© 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. 43471
    Prev
    Next
    INDEX
    Explanations

    Code and names

    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
     resting
    -0.46
     rests
    -0.38
    rest
    -0.36
     ball
    -0.34
     rest
    -0.34
     Rest
    -0.33
    -rest
    -0.33
     rested
    -0.32
     bolt
    -0.31
    ä¼ijæģ¯
    -0.30
    POSITIVE LOGITS
     links
    0.28
     link
    0.27
    arem
    0.26
    ç«
    0.26
    -link
    0.26
    esModule
    0.25
    Link
    0.25
     SV
    0.24
    blo
    0.24
    _links
    0.24
    Activations Density 0.003%

    No Known Activations