© 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. 99138
    Prev
    Next
    INDEX
    Explanations

    almost

    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
    itty
    -0.24
    arga
    -0.23
    æľīéĴ±
    -0.23
    çĥı
    -0.23
    structure
    -0.23
     pocket
    -0.23
    beg
    -0.23
     behold
    -0.23
     amo
    -0.23
    Ŭ
    -0.22
    POSITIVE LOGITS
    åįİ举
    0.26
    eler
    0.24
     younger
    0.24
    Ĺı
    0.24
    -east
    0.24
    å¥ĩ
    0.23
    esan
    0.23
     buc
    0.23
    udiant
    0.23
     Importance
    0.23
    Activations Density 0.013%

    No Known Activations