© 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. 14-TRANSCODER-HP
    7. 39435
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æŀ¸
    -0.29
    ille
    -0.29
     completes
    -0.27
    ä¸į容
    -0.27
    è¿ĺåľ¨
    -0.27
     impressed
    -0.26
    ima
    -0.25
    å¥¹åľ¨
    -0.25
    è¿ĺæľīä»Ģä¹Ī
    -0.25
     Comple
    -0.24
    POSITIVE LOGITS
    wich
    0.30
    Hi
    0.28
    躯
    0.27
    eni
    0.27
    æ¡Ī
    0.26
    è´¨
    0.26
    elves
    0.24
    æīĭå¥Ĺ
    0.24
    Marshal
    0.23
    ä¸ĭæīĭ
    0.23
    Activations Density 0.210%

    No Known Activations