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. 24493
    Prev
    Next
    INDEX
    Explanations

    basis

    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
    -Version
    -0.07
     utilizando
    -0.07
     כמובן
    -0.07
    icester
    -0.07
    inidad
    -0.07
    ertino
    -0.06
     cet
    -0.06
     Alternatively
    -0.06
    __/
    -0.06
    逐一
    -0.06
    POSITIVE LOGITS
     topical
    0.07
     Nail
    0.07
    办公
    0.07
    (question
    0.07
    的声音
    0.07
    _COMPONENT
    0.06
    .Collection
    0.06
    质
    0.06
    -question
    0.06
     spell
    0.06
    Activations Density 0.191%

    No Known Activations