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. 23-TRANSCODER-HP
    4. 15149
    Prev
    Next
    INDEX
    Explanations

    Current events and economy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åİĨ
    -0.29
    clo
    -0.29
    WebpackPlugin
    -0.27
    endid
    -0.27
    ç¼ĸåζ
    -0.26
    èĩ¾
    -0.25
     Contributor
    -0.25
     trouble
    -0.25
     Contributions
    -0.25
    dress
    -0.24
    POSITIVE LOGITS
     flo
    0.29
    å½ĵä»Ĭ
    0.28
    quam
    0.26
     today
    0.26
     unfit
    0.26
    溢
    0.25
     Today
    0.25
    ç¢İçīĩ
    0.25
    ä»Ĭ天çļĦ
    0.25
     amid
    0.24
    Activations Density 0.006%

    No Known Activations