Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 56516
    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
    克
    -0.09
     vis
    -0.07
    ль
    -0.07
    .constraint
    -0.07
     compliment
    -0.07
    _generic
    -0.06
     nc
    -0.06
    струк
    -0.06
    遠
    -0.06
    WEB
    -0.06
    POSITIVE LOGITS
    Perl
    0.08
    Reason
    0.07
    试图
    0.07
    .RowStyle
    0.07
     forState
    0.06
     mau
    0.06
    /the
    0.06
     Jud
    0.06
    _BUFFER
    0.06
    loadModel
    0.06
    Activations Density 0.003%

    No Known Activations