© 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. 33-TRANSCODER-HP
    7. 52980
    Prev
    Next
    INDEX
    Explanations

    do

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    not
    -0.39
     not
    -0.36
    ä¸įä»ħæĺ¯
    -0.32
    -not
    -0.31
    ä¸įä»ħ
    -0.30
    .not
    -0.30
    ä¸įä»ħä»ħæĺ¯
    -0.30
     Not
    -0.30
    ä¸įæĺ¯
    -0.29
    æĪĹ
    -0.28
    POSITIVE LOGITS
    pt
    0.34
     amount
    0.31
    vr
    0.28
    xm
    0.28
     imp
    0.26
    xn
    0.25
    xis
    0.25
    dm
    0.25
     Ao
    0.25
    xo
    0.25
    Activations Density 0.023%

    No Known Activations