© 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. 41787
    Prev
    Next
    INDEX
    Explanations

    code/technical documentation

    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
    ainers
    -0.29
    çľĭä¸įæĩĤ
    -0.28
     Ignore
    -0.27
    utes
    -0.27
    sitemap
    -0.26
    é»ijæģ¶åĬ¿åĬĽ
    -0.26
    (({
    -0.24
    räg
    -0.24
    onso
    -0.23
    åİŁæĿIJæĸĻ
    -0.23
    POSITIVE LOGITS
     close
    0.28
     closer
    0.28
     scope
    0.28
    æĽ²
    0.28
     sy
    0.27
     scop
    0.26
     closest
    0.26
     fine
    0.26
     dedicated
    0.26
     clear
    0.25
    Activations Density 0.000%

    No Known Activations