© 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. 31-TRANSCODER-HP
    7. 18413
    Prev
    Next
    INDEX
    Explanations

    act

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Well
    -0.29
    нÑĥл
    -0.28
    (CultureInfo
    -0.26
    /Internal
    -0.26
    etty
    -0.26
    æºĸ
    -0.25
    ãģ¨ãģĦãģ£ãģ¦ãĤĤ
    -0.25
     well
    -0.25
    etsy
    -0.25
    .opensource
    -0.24
    POSITIVE LOGITS
     upon
    0.43
     directly
    0.37
    upon
    0.31
    Upon
    0.31
    wij
    0.30
     best
    0.29
     much
    0.29
     Upon
    0.29
     on
    0.28
    much
    0.28
    Activations Density 0.889%

    No Known Activations