© 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. 142609
    Prev
    Next
    INDEX
    Explanations

    instructions, options

    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
    æľ¬èº«çļĦ
    -0.28
    å®Į
    -0.27
    鸣
    -0.27
    æŃ£ä¹ī
    -0.26
    æĽ´æĸ°
    -0.26
     gravity
    -0.26
    æķ´ä½ĵ
    -0.26
    åīįçŀ»
    -0.25
    ä¸įåĥı
    -0.25
    åĵį
    -0.25
    POSITIVE LOGITS
     Obs
    0.28
    个交æĺĵæĹ¥
    0.27
     confess
    0.27
     #__
    0.26
    ::$_
    0.25
     speculate
    0.25
    #__
    0.24
    ancellationToken
    0.24
    [$_
    0.24
    otos
    0.24
    Activations Density 25.400%

    No Known Activations