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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 76171
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    .exam
    -0.07
     tan
    -0.07
    快递
    -0.07
     Corvette
    -0.07
    apps
    -0.06
    NoArgsConstructor
    -0.06
     Burnett
    -0.06
     submarine
    -0.06
    Platforms
    -0.06
    tras
    -0.06
    POSITIVE LOGITS
     yerleş
    0.08
    美好的
    0.07
     decid
    0.07
     Searching
    0.07
    整天
    0.07
     sequ
    0.07
    _linked
    0.07
     incor
    0.07
    служ
    0.06
    ível
    0.06
    Activations Density 0.004%

    No Known Activations