© 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. 17872
    Prev
    Next
    INDEX
    Explanations

    online

    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
    å»ºåĽ½
    -0.30
     '
    -0.29
     erklärt
    -0.27
    æķ°
    -0.26
     '--
    -0.26
    Sc
    -0.26
     Shoe
    -0.26
    '
    -0.25
    åIJĪ
    -0.25
     Sc
    -0.25
    POSITIVE LOGITS
    .catalog
    0.35
     databases
    0.34
     catalogs
    0.34
     catalog
    0.33
    BOSE
    0.32
    catalog
    0.32
    _catalog
    0.32
     directory
    0.31
    /options
    0.31
    positories
    0.30
    Activations Density 0.835%

    No Known Activations