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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 4717
    Prev
    Next
    INDEX
    Explanations

    the

    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
    åĴĮ社ä¼ļ
    -0.28
    tfoot
    -0.26
    èĤ¤
    -0.25
     fool
    -0.24
    ĽĦ
    -0.24
    leen
    -0.24
    å½ĵä»ĸ
    -0.24
    eca
    -0.23
    çķ
    -0.23
    åIJİå¤ĩ
    -0.23
    POSITIVE LOGITS
     motions
    0.26
    t
    0.25
    emed
    0.24
    /umd
    0.24
    .comm
    0.24
    çľĭæĿ¥
    0.24
    layın
    0.23
    à¹Ģà¸ľ
    0.23
    .Initial
    0.23
    _SERIAL
    0.23
    Activations Density 0.263%

    No Known Activations