© 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. 15-RESID-POST-AA
    6. 28203
    Prev
    Next
    INDEX
    Explanations

    Comic books

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    achelor
    -0.07
    ᨩ
    -0.06
    捍卫
    -0.06
    北部
    -0.06
    .getToken
    -0.06
     Alic
    -0.06
     sophistic
    -0.06
    ":@"
    -0.06
    Lint
    -0.06
    .Ref
    -0.06
    POSITIVE LOGITS
    Shot
    0.07
    sexo
    0.07
     ausge
    0.07
     projected
    0.07
    Mobile
    0.07
     wiki
    0.07
     가져
    0.07
     shoreline
    0.07
    ırl
    0.07
     şa
    0.06
    Activations Density 0.039%

    No Known Activations