© 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. 5442
    Prev
    Next
    INDEX
    Explanations

    Special characters

    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
     Edit
    -0.27
    Locator
    -0.26
     Hearth
    -0.26
     scales
    -0.25
    ä¸ĢéĿ¢
    -0.24
    .dependencies
    -0.24
    éĹŃ
    -0.24
     Foundations
    -0.23
    bread
    -0.23
    _locator
    -0.23
    POSITIVE LOGITS
    yne
    0.28
    ynes
    0.28
    åīįèĢħ
    0.27
    CJK
    0.26
     theirs
    0.26
    rett
    0.26
    åķĨæĬ¥
    0.25
    ÑģÑĤавка
    0.25
    rian
    0.24
     multiline
    0.24
    Activations Density 0.015%

    No Known Activations