© 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. 29110
    Prev
    Next
    INDEX
    Explanations

    to

    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
    é¦Ī
    -0.28
    artment
    -0.27
    straction
    -0.26
    RON
    -0.26
    å¥Ĺ
    -0.26
    ICS
    -0.26
    .reference
    -0.25
    á¿Ĩ
    -0.25
    stanbul
    -0.24
    å¼ķçĶ¨
    -0.24
    POSITIVE LOGITS
    imet
    0.29
    ãĤ³ãĥŁãĥ¥ãĥĭãĤ±
    0.27
    âĢ¦and
    0.27
    è¿¢
    0.27
    )&&(
    0.25
     Cougar
    0.25
    –and
    0.24
     mediums
    0.24
    æ¬ºè´Ł
    0.24
    ä¸įèĪį
    0.24
    Activations Density 1.021%

    No Known Activations