© 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. 17787
    Prev
    Next
    INDEX
    Explanations

    technical/military contexts

    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
     line
    -0.36
     Line
    -0.33
    line
    -0.32
     lines
    -0.31
    Line
    -0.31
    éĴī
    -0.28
     getline
    -0.27
    lines
    -0.27
    iline
    -0.27
    ãĥ©ãĤ¤ãĥ³
    -0.26
    POSITIVE LOGITS
    è§Ĵ
    0.28
     units
    0.28
    -unit
    0.27
    åĬĽ
    0.26
    gles
    0.25
    encers
    0.25
    поÑĢ
    0.25
    gp
    0.25
     Ary
    0.24
    units
    0.24
    Activations Density 0.006%

    No Known Activations