© 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. 67911
    Prev
    Next
    INDEX
    Explanations

    umb

    np_max-act · gemini-2.0-flash
    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
    这让
    -0.07
    .elapsed
    -0.07
    太大
    -0.07
    魆
    -0.07
    (scan
    -0.07
    🥶
    -0.07
    apollo
    -0.07
    深入开展
    -0.07
    驻村
    -0.07
    ]}
    -0.07
    POSITIVE LOGITS
    格會
    0.07
    ﮑ
    0.07
    좌
    0.07
    ώ
    0.07
    мат
    0.07
    MOST
    0.07
    rical
    0.07
     customary
    0.06
    𝕣
    0.06
    AccessorType
    0.06
    Activations Density 0.003%

    No Known Activations