© 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. 42845
    Prev
    Next
    INDEX
    Explanations

    levels

    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
    reno
    -0.29
    eous
    -0.28
    uci
    -0.27
    upy
    -0.25
    abies
    -0.24
    cul
    -0.24
    iren
    -0.24
    umble
    -0.23
    oulos
    -0.23
    ç«ŀ
    -0.23
    POSITIVE LOGITS
     levels
    1.67
     level
    1.65
     Levels
    1.48
    æ°´å¹³
    1.46
    level
    1.43
    levels
    1.43
     Level
    1.41
    Level
    1.36
    _level
    1.34
     LEVEL
    1.33
    Activations Density 0.006%

    No Known Activations