© 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. 64751
    Prev
    Next
    INDEX
    Explanations

    unable

    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
    ĥĿ
    -0.25
     VERY
    -0.25
    Õ§
    -0.24
    PARAM
    -0.24
    éĿŀ常å¤ļ
    -0.24
    çļĦæīĢæľī
    -0.23
    å¦Ĥæŀľæĺ¯
    -0.23
     eer
    -0.23
    *&
    -0.23
    æĦŁè°¢
    -0.23
    POSITIVE LOGITS
    ä¹¾
    0.26
     Devin
    0.25
    aina
    0.24
    ê¹Į
    0.24
    abyrinth
    0.24
     Gratis
    0.24
    gratis
    0.24
    gnore
    0.23
    rador
    0.23
    /kubernetes
    0.23
    Activations Density 31.207%

    No Known Activations