© 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. 108116
    Prev
    Next
    INDEX
    Explanations

    medical and scientific texts

    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
    asonic
    -0.27
    automatic
    -0.26
    unk
    -0.25
    åıij
    -0.25
    reno
    -0.25
    ogne
    -0.24
    alg
    -0.24
    æĬĹè®®
    -0.24
    angan
    -0.23
    丹
    -0.23
    POSITIVE LOGITS
     shuttle
    0.32
    adder
    0.28
    gui
    0.27
    tte
    0.26
     Shuttle
    0.26
     bam
    0.25
    dre
    0.25
    _HIDE
    0.25
    IDES
    0.24
    åIJijå¤ĸ
    0.24
    Activations Density 21.850%

    No Known Activations