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

    Neuronpedia

    APICircuit 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. 27-RESID-POST-AA
    6. 131051
    Prev
    Next
    INDEX
    Explanations

    '/

    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_27/trainer_1
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _sol
    -0.08
    ऐ
    -0.07
    生病
    -0.07
    瞬
    -0.07
    役
    -0.07
    嵇
    -0.07
    оор
    -0.07
    砬
    -0.06
    仪器
    -0.06
    样子
    -0.06
    POSITIVE LOGITS
     disposing
    0.07
    '=>'
    0.07
     Erdogan
    0.07
     />';↵
    0.07
    :])↵
    0.06
    -----------*/↵
    0.06
     /><
    0.06
     Bruce
    0.06
     fooled
    0.06
    ニング
    0.06
    Activations Density 0.026%

    No Known Activations