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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 11-TRANSCODER-HP
    4. 146269
    Prev
    Next
    INDEX
    Explanations

    business/organizational descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Separated
    -0.28
    åIJĪä¼Ļ人
    -0.25
    á»ī
    -0.25
    sal
    -0.24
    ounge
    -0.23
     Eis
    -0.23
     Instructions
    -0.23
    elling
    -0.23
    ottes
    -0.23
    chter
    -0.23
    POSITIVE LOGITS
    è¯įæĿ¡
    0.29
    URE
    0.29
    hek
    0.28
    ä¸ĩå®¶
    0.27
    åħµåĽ¢
    0.24
    æĥ³è±¡
    0.24
    çĵ®
    0.24
    è·ijåΰ
    0.24
    _PA
    0.24
     Kee
    0.23
    Activations Density 0.017%

    No Known Activations