© 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. 17927
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    (ord
    -0.28
    åĶĩ
    -0.26
    åįİ侨
    -0.26
    ated
    -0.25
    ส
    -0.25
    âĸ½
    -0.25
    OSH
    -0.24
    redo
    -0.24
     burned
    -0.24
    &w
    -0.24
    POSITIVE LOGITS
    forming
    0.29
     patri
    0.28
     Steele
    0.25
    æĶ¾å¿ĥ
    0.25
    agli
    0.24
    æĿIJ
    0.24
     TCL
    0.24
    UF
    0.24
    kaar
    0.24
    -quarters
    0.24
    Activations Density 0.007%

    No Known Activations