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. 11-RESID-POST-AA
    6. 1992
    Prev
    Next
    INDEX
    Explanations

    0

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    禁区
    -0.07
    ("")
    -0.07
    谚
    -0.07
     "'";↵
    -0.06
     ())
    -0.06
     trotz
    -0.06
    ucz
    -0.06
    tim
    -0.06
    _timeline
    -0.06
    .pat
    -0.06
    POSITIVE LOGITS
     result
    0.07
     watch
    0.07
     material
    0.07
     Exec
    0.07
     processing
    0.07
     ser
    0.07
    	control
    0.07
    work
    0.07
     Matcher
    0.07
     reven
    0.07
    Activations Density 0.042%

    No Known Activations