© 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. 9-TRANSCODER-HP
    7. 29787
    Prev
    Next
    INDEX
    Explanations

    care

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¾ĭ
    -0.31
     wired
    -0.28
    [Unit
    -0.28
    ellar
    -0.27
    vier
    -0.26
    åħijçİ°
    -0.25
    ä¸ºçĽ®çļĦ
    -0.25
    sty
    -0.24
     wiring
    -0.24
    rès
    -0.24
    POSITIVE LOGITS
    åĪĨä¼ļ
    0.26
     DISCLAIMS
    0.26
    gue
    0.25
    éĥ¨åī¯éĥ¨éķ¿
    0.25
    误差
    0.24
    çľļ
    0.24
     bä
    0.24
     Richardson
    0.24
    rt
    0.23
    çݯæ¯Ķ
    0.23
    Activations Density 0.406%

    No Known Activations