© 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. 5307
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    SPATH
    -0.27
    fone
    -0.27
    etz
    -0.25
    èĩ¾
    -0.25
    å¹´ä¹ĭ
    -0.25
     cop
    -0.23
    ä¸į解
    -0.23
    кла
    -0.23
    kB
    -0.23
    GRAM
    -0.23
    POSITIVE LOGITS
    äººåľ¨
    0.26
    *pow
    0.24
    dling
    0.24
    åĪ¥
    0.24
    åĪ«
    0.23
    pread
    0.23
     rar
    0.23
    æĮĤçīĮ
    0.23
    åºĸ
    0.23
    omez
    0.23
    Activations Density 0.046%

    No Known Activations

    This feature has no known activations.