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. 88310
    Prev
    Next
    INDEX
    Explanations

    IX

    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
     vì
    -0.07
    MethodName
    -0.07
    Amt
    -0.07
     مدينة
    -0.07
    妆
    -0.07
    tte
    -0.07
     mug
    -0.06
     Gauss
    -0.06
     Vernon
    -0.06
    _matching
    -0.06
    POSITIVE LOGITS
     pthread
    0.08
     elim
    0.08
     FAILURE
    0.07
     conex
    0.07
     enumerate
    0.07
    LIMIT
    0.07
    }});↵
    0.07
    (media
    0.07
    Combine
    0.07
     FILTER
    0.07
    Activations Density 0.000%

    No Known Activations