© 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. 41942
    Prev
    Next
    INDEX
    Explanations

    cost

    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
    èĢĮæĪIJ
    -0.28
    pard
    -0.28
    éĺ»ç¢į
    -0.27
    ìĽĶ
    -0.27
    è´¢æĶ¿
    -0.27
    iced
    -0.26
    æľīåºı
    -0.26
    .im
    -0.25
     Season
    -0.25
    alog
    -0.25
    POSITIVE LOGITS
    åģļ人
    0.28
     distinction
    0.27
    âĺī
    0.26
     model
    0.26
    æĻķ
    0.26
     stake
    0.25
    æķĪ
    0.25
     comes
    0.24
     differential
    0.24
     mies
    0.24
    Activations Density 0.006%

    No Known Activations