© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 68850
    Prev
    Next
    INDEX
    Explanations

    by

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DBNull
    -0.07
    疭
    -0.07
    Trigger
    -0.07
     getattr
    -0.07
     BitSet
    -0.07
     getMax
    -0.07
    esthes
    -0.06
    ewolf
    -0.06
    เทรด
    -0.06
    hiếu
    -0.06
    POSITIVE LOGITS
    ().↵
    0.08
    保留
    0.08
    ريس
    0.07
    起到了
    0.07
    饭
    0.07
    宽敞
    0.07
    .details
    0.07
    okies
    0.07
     definition
    0.07
    翠
    0.07
    Activations Density 0.030%

    No Known Activations