© 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. 9-TRANSCODER-HP
    7. 29311
    Prev
    Next
    INDEX
    Explanations

    renal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    带走
    -0.28
    à´·
    -0.27
    æł·çļĦ
    -0.27
    伤çĹħ
    -0.25
    秣éĩij
    -0.25
    ccb
    -0.25
    ç§ģä¸ĭ
    -0.25
    ìĬ¨
    -0.24
     olu
    -0.24
    érc
    -0.24
    POSITIVE LOGITS
    [array
    0.31
    .Edit
    0.28
     supermarket
    0.27
    redit
    0.26
    [next
    0.25
    éĦĻ
    0.25
     vul
    0.25
    æ¤IJ
    0.24
    atrix
    0.24
    棣
    0.24
    Activations Density 1.639%

    No Known Activations