© 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. 128940
    Prev
    Next
    INDEX
    Explanations

    research papers

    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
     UNKNOWN
    -0.28
    ibur
    -0.27
    ä¸įä¸Ģæł·
    -0.26
    ateral
    -0.26
    æĿIJ
    -0.26
    errupted
    -0.26
    -awesome
    -0.25
     unknown
    -0.25
    æĸ°éĹ»ä¸Ńå¿ĥ
    -0.24
    éĶ¥
    -0.24
    POSITIVE LOGITS
    thon
    0.28
    çĸı
    0.25
    bell
    0.25
    illon
    0.25
    uci
    0.25
    åĭĴ
    0.24
     LENG
    0.24
    _extraction
    0.24
    缨
    0.24
    ivy
    0.24
    Activations Density 0.033%

    No Known Activations