© 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. 43162
    Prev
    Next
    INDEX
    Explanations

    Events and meetings

    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
    OfYear
    -0.28
    olib
    -0.28
     year
    -0.28
    stoff
    -0.27
     #####
    -0.26
    ç½²
    -0.26
    (place
    -0.26
    ç¬ijè¯Ŀ
    -0.25
    _INITIALIZER
    -0.25
    åݻ买
    -0.25
    POSITIVE LOGITS
     Meeting
    0.29
     topped
    0.29
    elight
    0.29
    eda
    0.28
     headed
    0.28
    FEATURE
    0.28
     held
    0.28
    ana
    0.27
    hana
    0.27
    å¼Ĭ
    0.27
    Activations Density 0.030%

    No Known Activations