© 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. 141658
    Prev
    Next
    INDEX
    Explanations

    of

    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
     Trustees
    -0.28
    spinner
    -0.27
    ÑĥÑĤ
    -0.26
     Tk
    -0.26
    enan
    -0.25
    ako
    -0.25
    rike
    -0.25
    หลวà¸ĩ
    -0.25
    лик
    -0.24
    getFile
    -0.24
    POSITIVE LOGITS
    in
    0.27
    owed
    0.26
    niejs
    0.25
    沤
    0.25
    ä¸įå½±åĵį
    0.24
    主æĦı
    0.24
    orent
    0.24
    éĽ
    0.24
    nder
    0.23
    aud
    0.23
    Activations Density 0.896%

    No Known Activations