© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41925
    Prev
    Next
    INDEX
    Explanations

    Legal districts and judges

    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
     shard
    -0.06
    QueryBuilder
    -0.06
     electorate
    -0.06
    借錢
    -0.06
     uz
    -0.06
    oins
    -0.06
     throwError
    -0.06
     prelim
    -0.06
     anglais
    -0.06
    wort
    -0.06
    POSITIVE LOGITS
    茶
    0.07
    Ter
    0.07
     Broker
    0.07
     eating
    0.07
    CGSize
    0.06
    _SER
    0.06
    -launch
    0.06
     Tag
    0.06
    噼
    0.06
    estring
    0.06
    Activations Density 0.001%

    No Known Activations