© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 22260
    Prev
    Next
    INDEX
    Explanations

    manipulate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fried
    -0.29
    lide
    -0.28
    æĻļæĬ¥
    -0.27
    æĢĿç´¢
    -0.25
    ospace
    -0.25
    çħ¨
    -0.25
    æħĪ
    -0.24
    orning
    -0.24
    CARD
    -0.24
     hourly
    -0.24
    POSITIVE LOGITS
    çī¹æĿĥ
    0.26
     Shack
    0.26
    å¸ĤåľºéľĢæ±Ĥ
    0.26
    [r
    0.25
    //@
    0.24
    åĪĨå·¥
    0.24
    æİĴè¡Įæ¦ľ
    0.24
    ::*
    0.24
    æīįçŁ¥éģĵ
    0.24
     BRA
    0.23
    Activations Density 0.087%

    No Known Activations