© 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. 53708
    Prev
    Next
    INDEX
    Explanations

    W

    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
     round
    -0.32
     rounded
    -0.29
    -round
    -0.28
     gran
    -0.28
     rules
    -0.27
    yst
    -0.27
     notch
    -0.27
     ROUND
    -0.27
     rounds
    -0.26
     capped
    -0.26
    POSITIVE LOGITS
    ä½ĵåĨħ
    0.29
    Õ³
    0.26
    eworthy
    0.25
    ä¸įç¡®å®ļæĢ§
    0.24
    resenter
    0.24
     Rhodes
    0.24
    ĤŃ
    0.23
    Hyper
    0.23
     Datum
    0.23
    ä¸¤å¼ł
    0.23
    Activations Density 0.014%

    No Known Activations