© 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. 43651
    Prev
    Next
    INDEX
    Explanations

    There is nothing in common.8

    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
     August
    -0.35
     eight
    -0.31
     diss
    -0.31
    åħ«ä¸ª
    -0.30
    August
    -0.28
     Eighth
    -0.28
    åįģåħ«æĿ¡
    -0.28
     Qual
    -0.27
    eight
    -0.27
    稷
    -0.27
    POSITIVE LOGITS
    amber
    0.28
    åĨ¬å¥¥
    0.27
    çłĶ
    0.26
    ç¡ķ士çłĶ究
    0.26
     Sachs
    0.26
    çļĦåľ°åĽ¾
    0.25
    oes
    0.25
    ä¹Ŀ
    0.25
    lag
    0.24
    esso
    0.24
    Activations Density 0.009%

    No Known Activations