© 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. 9-TRANSCODER-HP
    7. 30455
    Prev
    Next
    INDEX
    Explanations

    (

    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
    Negative Logits
    Assign
    -0.26
    йÑĤеÑģÑĮ
    -0.25
    éĹ¼
    -0.25
     teammates
    -0.25
    دة
    -0.25
    大夫
    -0.24
    éĺŁåıĭ
    -0.24
    assign
    -0.24
     MatDialog
    -0.24
    Freq
    -0.24
    POSITIVE LOGITS
    urve
    0.28
    æĤ¬
    0.27
    inem
    0.27
    æ·±
    0.26
     doub
    0.25
    ulong
    0.25
    èĭ±æł¼åħ°
    0.24
     Kickstarter
    0.24
    ablo
    0.24
    iets
    0.24
    Activations Density 0.592%

    No Known Activations