© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5730
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rats
    -0.30
    odate
    -0.27
    ero
    -0.26
     chá
    -0.26
     RootState
    -0.25
    åĬłçĽŁåºĹ
    -0.25
    .Areas
    -0.24
    Groups
    -0.24
     Presented
    -0.24
    IMA
    -0.24
    POSITIVE LOGITS
    çļĦåIJĦç§į
    0.30
    å¸Į
    0.29
    æłĩå¿ĹæĢ§
    0.28
    EMENT
    0.26
     Ezek
    0.26
     fj
    0.26
    .exports
    0.25
    ä¸ŃçļĦ
    0.25
    tons
    0.25
    两æĿ¡
    0.25
    Activations Density 0.150%

    No Known Activations