© 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. 88864
    Prev
    Next
    INDEX
    Explanations

    Citations

    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
    -sample
    -0.28
    icts
    -0.28
    ä¿¡ç®±
    -0.27
    ç½ijåıĭè¯Ħ论
    -0.27
     biologist
    -0.26
    åīįä¸įä¹ħ
    -0.26
    -authored
    -0.25
    icted
    -0.25
     catch
    -0.25
    çĶ±ä¸ŃåĽ½
    -0.24
    POSITIVE LOGITS
     (
    0.30
     (+
    0.29
     Sle
    0.26
    xy
    0.26
    订
    0.25
    Formatted
    0.25
    undry
    0.25
    è¯Ħè®®
    0.25
    ucle
    0.24
    æ¦Ĥ念
    0.24
    Activations Density 0.004%

    No Known Activations