© 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. 32-TRANSCODER-HP
    7. 42754
    Prev
    Next
    INDEX
    Explanations

    links or code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    F
    -0.31
    upon
    -0.29
    ña
    -0.27
     midway
    -0.27
    ADED
    -0.27
    aaa
    -0.26
    hev
    -0.26
     Nev
    -0.26
    ãģ¿
    -0.26
    H
    -0.26
    POSITIVE LOGITS
    empre
    0.31
    ä¸Ģç«Ļ
    0.28
    .tk
    0.28
    .Inst
    0.27
    ermint
    0.27
    oler
    0.26
    鸯
    0.26
     democr
    0.26
    aken
    0.26
    dent
    0.26
    Activations Density 0.001%

    No Known Activations