© 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. 87002
    Prev
    Next
    INDEX
    Explanations

    medical

    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
    ients
    -0.27
    ÙĦاÙĦ
    -0.26
    çºĤ
    -0.26
    lates
    -0.24
     stretch
    -0.24
     chained
    -0.23
    让åŃ©åŃIJ
    -0.23
     heartbeat
    -0.23
    Globals
    -0.23
    LLU
    -0.23
    POSITIVE LOGITS
    ç¡®
    0.26
    çĥŁèĬ±
    0.26
    èĪĴéĢĤ
    0.25
    èĤī
    0.25
    (pc
    0.24
    ,GL
    0.23
    ç¢İ
    0.23
     ÏĢ
    0.23
    çīĮ
    0.23
    åıĭ们
    0.23
    Activations Density 0.116%

    No Known Activations