© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 129181
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    lines of document-level metadata and formal headings (e.g., legal case headers, copyright/permission boilerplate, and other official title/metadata blocks).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    骄
    -0.07
    (sv
    -0.07
     viewType
    -0.07
    黏
    -0.07
     FORWARD
    -0.07
    opus
    -0.07
    夔
    -0.07
    妭
    -0.07
    BuilderInterface
    -0.07
     #{@
    -0.07
    POSITIVE LOGITS
    :↵↵
    0.14
    .↵↵
    0.13
    ↵↵
    0.13
    ↵
↵
    0.13
     (
    0.11
    )↵↵
    0.11
    :
↵
↵
    0.10
     .↵↵
    0.10
    0.10
    }↵↵
    0.09
    Activations Density 1.219%

    No Known Activations