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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19-RESID-POST-AA
    6. 6879
    Prev
    Next
    INDEX
    Explanations

    Definitions & code

    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
    ibt
    -0.07
    多名
    -0.07
    论坛
    -0.07
     Dodgers
    -0.07
    xyz
    -0.07
    '+
    -0.07
    ,right
    -0.07
     SearchResult
    -0.07
     executives
    -0.07
     צריכים
    -0.07
    POSITIVE LOGITS
    瞢
    0.07
     lessen
    0.07
    闻
    0.07
    ראש
    0.07
    corn
    0.07
    Reject
    0.07
    味
    0.07
    PARATOR
    0.06
    Pipe
    0.06
    paced
    0.06
    Activations Density 0.000%

    No Known Activations