© 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. 140902
    Prev
    Next
    INDEX
    Explanations

    News articles

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æĮij
    -0.30
    侧éĩį
    -0.26
    åľ¨æł¡
    -0.26
    èĸĦå¼±
    -0.26
     scri
    -0.24
    è¯¥æł¡
    -0.24
    modification
    -0.24
     Nack
    -0.24
    çĶŁåij½
    -0.24
    æ¯Ķè¾ĥç®Ģåįķ
    -0.24
    POSITIVE LOGITS
    âĹ»
    0.27
    flt
    0.26
     guess
    0.26
    æŁ¥æĺİ
    0.25
    inia
    0.24
    ophon
    0.23
    etable
    0.23
    _nh
    0.23
    itable
    0.23
    WEBPACK
    0.23
    Activations Density 12.302%

    No Known Activations