© 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. 30204
    Prev
    Next
    INDEX
    Explanations

    Technology, computers

    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
    åĤ¾
    -0.28
     draw
    -0.28
    è¿Ļä¸ī个
    -0.28
    è¿Ļæł·ä¸Ģ个
    -0.27
     Draw
    -0.26
    符åı·
    -0.26
     ven
    -0.26
    draw
    -0.26
    ä¹Łä¸į
    -0.25
    åIJĦæł·
    -0.25
    POSITIVE LOGITS
    .Fat
    0.27
    estre
    0.26
     confort
    0.26
    epy
    0.26
     Jew
    0.25
     POLIT
    0.25
    æĶ¿
    0.25
    缺å°ij
    0.25
    ubby
    0.24
    èĢĮåĩº
    0.24
    Activations Density 0.114%

    No Known Activations