© 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. 30-TRANSCODER-HP
    7. 95120
    Prev
    Next
    INDEX
    Explanations

    Cells

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Phát
    -0.29
    æīĴ
    -0.28
    æĽ³
    -0.28
     Bolton
    -0.28
    æĻ®åıĬ
    -0.27
     Vu
    -0.26
     Stanton
    -0.25
    genre
    -0.25
    avn
    -0.25
    led
    -0.25
    POSITIVE LOGITS
    ä½ĵ
    0.66
    ç»Ħç»ĩ
    0.65
     cells
    0.61
    ç»Ĩèĥŀ
    0.60
    é«Ķ
    0.56
     cell
    0.55
    çµĦç¹Ķ
    0.54
     Cells
    0.54
     organ
    0.54
     organism
    0.53
    Activations Density 1.026%

    No Known Activations