© 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. 20-TRANSCODER-HP
    7. 142589
    Prev
    Next
    INDEX
    Explanations

    generation/production

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å®ĮæĪIJäºĨ
    -0.30
     ao
    -0.27
    以ä¸ĬçļĦ
    -0.27
     proper
    -0.27
    esian
    -0.26
     recent
    -0.26
    å®ĮæĪIJ
    -0.26
    å®Įæķ´
    -0.26
    æĮº
    -0.26
    å®Įæķ´çļĦ
    -0.25
    POSITIVE LOGITS
    ially
    0.26
    ово
    0.26
    _RT
    0.25
    arily
    0.24
     bureaucr
    0.23
    ä¸ĭå·´
    0.23
    ä¸Ĭåİ»
    0.23
    emachine
    0.23
     nipples
    0.23
    æĤŃ
    0.23
    Activations Density 9.655%

    No Known Activations