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. 48533
    Prev
    Next
    INDEX
    Explanations

    uk

    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
    Anne
    -0.08
     lên
    -0.07
    issen
    -0.07
     Anne
    -0.07
    臧
    -0.07
    OLD
    -0.07
    nick
    -0.07
     Peter
    -0.07
     COLORS
    -0.07
     sped
    -0.07
    POSITIVE LOGITS
    uk
    0.08
    _market
    0.08
     Concat
    0.07
    -router
    0.07
    框架协议
    0.07
    агент
    0.07
     mechan
    0.07
     Sec
    0.07
    畴
    0.07
    믄
    0.07
    Activations Density 0.013%

    No Known Activations