© 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. 27-TRANSCODER-HP
    7. 58566
    Prev
    Next
    INDEX
    Explanations

    programming and web development

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Protector
    -0.28
     roads
    -0.25
    åĤ¨èĵĦ
    -0.24
    ogh
    -0.24
     mys
    -0.24
    æ·¡æ°´
    -0.23
    [Test
    -0.23
    åIJ¬
    -0.23
     hors
    -0.23
    rench
    -0.23
    POSITIVE LOGITS
    è·¨
    0.27
    <a
    0.27
    <small
    0.26
    =device
    0.25
    磶
    0.25
     service
    0.25
     game
    0.24
    æľįåĬ¡
    0.24
    æĶĺ
    0.23
    ä¼ģ
    0.23
    Activations Density 0.010%

    No Known Activations