© 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. 86955
    Prev
    Next
    INDEX
    Explanations

    Excerpts from varied documents

    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
    ãģ¿ãģ¾ãģĹãģŁ
    -0.27
    пиÑģÑĮ
    -0.27
    è°ģéĥ½
    -0.27
     lul
    -0.25
     skeptic
    -0.24
     Lords
    -0.24
    伯
    -0.24
    -sign
    -0.24
     satisfied
    -0.24
    ç¨Ģ
    -0.24
    POSITIVE LOGITS
    apia
    0.33
     dès
    0.27
    èĢĮçİ°åľ¨
    0.26
     continuum
    0.26
     VÅ©
    0.25
    交æµģåIJĪä½ľ
    0.25
    èıŁ
    0.25
    nova
    0.25
     Ferry
    0.24
    åī©ä¸ĭ
    0.24
    Activations Density 0.012%

    No Known Activations