© 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. 22-TRANSCODER-HP
    7. 99077
    Prev
    Next
    INDEX
    Explanations

    Numbers and measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    edly
    -0.30
    adol
    -0.28
    dataProvider
    -0.26
    bull
    -0.26
    æıIJä¾ĽåķĨ
    -0.26
    .self
    -0.24
    çĭ¬
    -0.24
    æĽ²
    -0.24
    禾
    -0.24
    eden
    -0.23
    POSITIVE LOGITS
    nestjs
    0.28
    ifu
    0.27
    æĶ¯éħį
    0.27
    _MATH
    0.23
     sick
    0.23
    ander
    0.22
    stry
    0.22
    æķijæ²»
    0.22
    导åIJij
    0.22
     pod
    0.22
    Activations Density 0.171%

    No Known Activations