© 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. 20-TRANSCODER-HP
    7. 62572
    Prev
    Next
    INDEX
    Explanations

    code/math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    chal
    -0.30
    éļĨ
    -0.28
     LAP
    -0.28
     Lic
    -0.26
    kul
    -0.26
     progressive
    -0.25
    UPLE
    -0.25
    ippers
    -0.24
     GPL
    -0.24
    iful
    -0.24
    POSITIVE LOGITS
    åĩĨåħ¥
    0.26
    带éĺŁ
    0.25
     Handy
    0.25
    ording
    0.25
    antry
    0.25
    assembly
    0.25
    ÑĥÑİÑī
    0.24
    éĤĦæľī
    0.24
    è¿ĺæľī
    0.24
    è¿ĻäºĽä¸ľè¥¿
    0.24
    Activations Density 26.045%

    No Known Activations