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. 109935
    Prev
    Next
    INDEX
    Explanations

    look at it

    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
    דף
    -0.08
    ifdef
    -0.07
     indulge
    -0.07
    QDebug
    -0.07
    뀐
    -0.07
    leitung
    -0.07
     Centre
    -0.07
     principal
    -0.06
     Chen
    -0.06
    fuscated
    -0.06
    POSITIVE LOGITS
     Mist
    0.08
     Rai
    0.07
    _views
    0.07
    _fl
    0.07
     Arm
    0.07
     البط
    0.07
     hunters
    0.07
    omitempty
    0.07
    haust
    0.06
     rt
    0.06
    Activations Density 0.209%

    No Known Activations