© 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 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. 70482
    Prev
    Next
    INDEX
    Explanations

    friend

    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
     Kurt
    -0.07
    กฎ
    -0.07
    山坡
    -0.06
    铁
    -0.06
    Intent
    -0.06
     Elle
    -0.06
    ndx
    -0.06
    тельно
    -0.06
     дир
    -0.06
    ㌢
    -0.06
    POSITIVE LOGITS
    (if
    0.07
    `}↵
    0.07
     irony
    0.07
    AMB
    0.07
    洗涤
    0.07
     athe
    0.07
     quotation
    0.07
    _ROLE
    0.07
    MESS
    0.06
     VARCHAR
    0.06
    Activations Density 0.001%

    No Known Activations