© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 108102
    Prev
    Next
    INDEX
    Explanations

    understanding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     `[
    -0.28
    ndon
    -0.26
    æĸ°é²ľ
    -0.26
    ][:
    -0.25
    _PACK
    -0.25
    æ½®
    -0.24
     fractional
    -0.24
    enberg
    -0.24
     humid
    -0.24
    chos
    -0.24
    POSITIVE LOGITS
    磼
    0.25
    åĬ³
    0.25
    _PIPE
    0.24
     Fantastic
    0.24
     Cornell
    0.24
    PIPE
    0.24
    ?
    0.23
    .copyOf
    0.23
    å©Ĩ
    0.23
    æĹłå¥Ī
    0.23
    Activations Density 16.033%

    No Known Activations