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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6741
    Prev
    Next
    INDEX
    Explanations

    Code and license agreement text

    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
    lim
    -0.27
    лим
    -0.26
    [I
    -0.26
    æ³³
    -0.26
    åĪĻæĺ¯
    -0.25
    æĺ¯ä»ĸ
    -0.25
    å·¥ä½ľå®¤
    -0.25
    eld
    -0.24
    char
    -0.24
    `(
    -0.24
    POSITIVE LOGITS
    æŦ
    0.30
    .mit
    0.28
    CPU
    0.24
    tons
    0.24
    __/
    0.24
    èĩªåıij
    0.24
    年第
    0.24
    æĢ»éĺŁ
    0.23
    ython
    0.23
    enden
    0.23
    Activations Density 1.666%

    No Known Activations