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. 19-RESID-POST-AA
    6. 36330
    Prev
    Next
    INDEX
    Explanations

    facts

    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
     (?
    -0.07
    ival
    -0.07
     rêve
    -0.07
     المس
    -0.07
    false
    -0.06
    /javascript
    -0.06
    Nil
    -0.06
    lık
    -0.06
     Monkey
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
     congreg
    0.07
    执法人员
    0.07
    运行
    0.07
    יצר
    0.07
    垢
    0.07
    ARSE
    0.07
    引进
    0.07
     порядке
    0.07
    条件下
    0.07
    禁毒
    0.06
    Activations Density 0.010%

    No Known Activations