© 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. 31-TRANSCODER-HP
    7. 19924
    Prev
    Next
    INDEX
    Explanations

    Computer networking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åij¼åIJ¸éģĵ
    -0.29
     Trey
    -0.26
    åįķä»·
    -0.25
    ãģ¹
    -0.25
    ophys
    -0.25
    wert
    -0.24
     Ped
    -0.23
    èĪŁ
    -0.23
     Proper
    -0.23
    ç¨į
    -0.23
    POSITIVE LOGITS
    å®īä¿Ŀ
    0.30
    çĥŁ
    0.29
     security
    0.29
    Smarty
    0.28
    æĢĿ
    0.28
    ä¹³
    0.28
    -sm
    0.27
    AA
    0.27
    íĻĪ
    0.26
     st
    0.26
    Activations Density 0.183%

    No Known Activations