© 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. 43466
    Prev
    Next
    INDEX
    Explanations

    introducing a clarification

    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
    where
    -0.35
     where
    -0.34
     Where
    -0.30
    	where
    -0.28
    kon
    -0.27
    Where
    -0.26
    带头人
    -0.26
    沸èħ¾
    -0.26
    骨
    -0.26
     disposed
    -0.26
    POSITIVE LOGITS
     operation
    0.36
    operation
    0.30
    tra
    0.30
     Operation
    0.29
    -operation
    0.28
     criminal
    0.27
     Article
    0.26
    åľ¨åħ¨åĽ½
    0.26
    .operation
    0.26
    _Execute
    0.26
    Activations Density 0.002%

    No Known Activations