© 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. 33-TRANSCODER-HP
    7. 54734
    Prev
    Next
    INDEX
    Explanations

    business and technology articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     minor
    -0.26
    ất
    -0.25
    icky
    -0.25
    -bed
    -0.25
    pir
    -0.25
    åĽ½å®¶
    -0.25
    acks
    -0.25
     unp
    -0.24
    .Web
    -0.24
    bed
    -0.24
    POSITIVE LOGITS
    anke
    0.27
    åģľçķĻ
    0.27
    åŃĹæ¯į
    0.24
    кеÑĢ
    0.24
    throw
    0.24
    alla
    0.24
    å¨ĥå¨ĥ
    0.23
    _builtin
    0.23
     Abstract
    0.23
    Entered
    0.23
    Activations Density 0.015%

    No Known Activations