© 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. 5207
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    å¨ĺ
    -0.25
     linewidth
    -0.24
     FP
    -0.24
     mouseClicked
    -0.24
    ucid
    -0.24
     funcion
    -0.23
    æ¼Ĩ
    -0.23
    墩
    -0.23
    onna
    -0.23
    åĨį
    -0.23
    POSITIVE LOGITS
    flows
    0.28
    archive
    0.26
    cff
    0.25
    ä¸ĩ个
    0.25
    igers
    0.24
    illions
    0.24
    right
    0.24
    alse
    0.24
    è´³
    0.24
    æĽ´é«ĺçļĦ
    0.23
    Activations Density 0.132%

    No Known Activations