© 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. 99025
    Prev
    Next
    INDEX
    Explanations

    Math/equations

    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
    a
    -0.30
    bery
    -0.28
    ALE
    -0.27
    ale
    -0.27
     gent
    -0.27
    umu
    -0.26
    å±¥
    -0.26
     piston
    -0.26
     lov
    -0.25
    çİĩåħĪ
    -0.24
    POSITIVE LOGITS
    åĶı
    0.29
    yers
    0.26
    yen
    0.26
    åIJĨ
    0.25
    -gallery
    0.25
    rolled
    0.24
    olars
    0.24
    个交æĺĵ
    0.24
    ota
    0.24
    _tel
    0.23
    Activations Density 0.121%

    No Known Activations