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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 115358
    Prev
    Next
    INDEX
    Explanations

    next

    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
     McGill
    -0.07
    ,img
    -0.07
    _bbox
    -0.07
    $stmt
    -0.06
    drs
    -0.06
    一架
    -0.06
     mile
    -0.06
     medieval
    -0.06
     pounds
    -0.06
     ):
    -0.06
    POSITIVE LOGITS
     portrayal
    0.07
     mutable
    0.07
    𝗕
    0.07
    的女人
    0.07
    ов
    0.06
    обеспечен
    0.06
     KEEP
    0.06
    Т
    0.06
     spéc
    0.06
    방송
    0.06
    Activations Density 0.000%

    No Known Activations