© 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. 20-TRANSCODER-HP
    7. 108575
    Prev
    Next
    INDEX
    Explanations

    alive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æĮģä¹ħ
    -0.43
    延ç»Ń
    -0.36
    æĮģç»Ń
    -0.35
    persistent
    -0.35
     perman
    -0.34
     Persistence
    -0.33
     persist
    -0.32
    æ°¸ä¸į
    -0.32
     indefinitely
    -0.31
     persists
    -0.31
    POSITIVE LOGITS
    转æį¢
    0.29
    第ä¸ĢæŃ¥
    0.26
    ationally
    0.25
     pon
    0.25
    å¾ĹåĪ°äºĨ
    0.24
    ä¹İ
    0.24
    Her
    0.24
    Converter
    0.24
    ifter
    0.23
    apot
    0.23
    Activations Density 15.679%

    No Known Activations