© 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. 43794
    Prev
    Next
    INDEX
    Explanations

    uniform

    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
    第ä¸Ģ
    -0.33
     first
    -0.31
    第ä¸Ģ个
    -0.30
     First
    -0.30
     пеÑĢвÑĥÑİ
    -0.29
    é¦ĸ个
    -0.29
    First
    -0.28
    zsche
    -0.28
     primeiro
    -0.27
    cession
    -0.26
    POSITIVE LOGITS
    ed
    0.37
    ity
    0.35
    ary
    0.29
    RY
    0.28
    typeid
    0.28
    ITY
    0.27
    足
    0.27
    ly
    0.27
    ely
    0.27
    edBy
    0.27
    Activations Density 0.003%

    No Known Activations