© 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. 19895
    Prev
    Next
    INDEX
    Explanations

    tasks

    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
    çļĦæĹ¥åŃIJ
    -0.27
    ixon
    -0.26
    çļĦ缮çļĦ
    -0.26
    à¹Īาà¸ĩ
    -0.26
    iry
    -0.26
    iral
    -0.25
    ä¸Ģåı£æ°Ķ
    -0.24
    çļĦæĦıè§ģ
    -0.24
    abox
    -0.24
    owy
    -0.24
    POSITIVE LOGITS
    ä»»
    0.82
    ãĤ¿
    0.61
     tas
    0.56
    -t
    0.52
     ta
    0.47
     ÑĤ
    0.45
    ask
    0.43
    tas
    0.43
     t
    0.43
    å¡Ķ
    0.43
    Activations Density 8.085%

    No Known Activations