© 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. 29375
    Prev
    Next
    INDEX
    Explanations

    time

    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
    pb
    -0.29
    访
    -0.28
    orra
    -0.27
    ercul
    -0.27
    æĺ¯éĿŀ
    -0.26
    éĵĹ
    -0.26
    ä¸įçIJĨ
    -0.26
    èĤ
    -0.25
    dziaÅĤ
    -0.25
    岬
    -0.24
    POSITIVE LOGITS
     enfer
    0.28
     CF
    0.25
    å½ĵä¹ĭ
    0.24
    ulfilled
    0.24
    è¾ĵéĢģ
    0.24
    å½ĵæĪij
    0.24
    大éĩıçļĦ
    0.24
    é£İæ°´
    0.23
    trained
    0.23
    çļĦäºĭå®ŀ
    0.23
    Activations Density 1.349%

    No Known Activations