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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 19-RESID-POST-AA
    11. 9122
    Prev
    Next
    INDEX
    Explanations

    coding and data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     epoxy
    -0.07
     fault
    -0.07
    oltage
    -0.06
     suis
    -0.06
     getSupportActionBar
    -0.06
     Adapter
    -0.06
    صلا
    -0.06
    🅴
    -0.06
     detalles
    -0.06
    igDecimal
    -0.06
    POSITIVE LOGITS
    向记者
    0.07
    CanBeConverted
    0.06
    .must
    0.06
    腨
    0.06
    Dub
    0.06
    迷信
    0.06
    gone
    0.06
     },
↵
↵
    0.06
    li
    0.06
    nostic
    0.06
    Activations Density 0.046%

    No Known Activations