© 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. 89002
    Prev
    Next
    INDEX
    Explanations

    Code and website content

    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
    folio
    -0.32
     Strategy
    -0.28
     WELL
    -0.28
    æĬĬæı¡
    -0.28
     alignments
    -0.27
     wellness
    -0.27
    é³Ł
    -0.26
    ategy
    -0.26
     Sustainable
    -0.26
    esson
    -0.26
    POSITIVE LOGITS
    è¾į
    0.28
    å»īä»·
    0.28
     cheap
    0.27
     rum
    0.27
    製
    0.26
    çīĮçħ§
    0.26
    浩
    0.25
    åĿŀ
    0.25
    æĨ¶
    0.25
    oret
    0.24
    Activations Density 0.003%

    No Known Activations