© 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. 84147
    Prev
    Next
    INDEX
    Explanations

    banking and finance

    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
    -process
    -0.07
     getP
    -0.07
    /tmp
    -0.07
     scrapped
    -0.07
    ᶏ
    -0.07
     sacr
    -0.06
     inception
    -0.06
     sour
    -0.06
    封面
    -0.06
    جبهة
    -0.06
    POSITIVE LOGITS
    两家
    0.08
     或
    0.07
    或其他
    0.07
    两个
    0.07
     יל
    0.07
    .QLabel
    0.07
    sto
    0.07
    kill
    0.07
    --------------------------------------------------------------------------------
    0.07
     Pet
    0.07
    Activations Density 0.012%

    No Known Activations