© 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. 106808
    Prev
    Next
    INDEX
    Explanations

    Common words

    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
    rgan
    -0.28
     cvs
    -0.28
    ä¹Łæ²¡æľī
    -0.27
    è¿ĺä¸įå¦Ĥ
    -0.27
    adle
    -0.25
     lack
    -0.24
     ammo
    -0.24
    ead
    -0.24
    ä¹Łä¸įèĥ½
    -0.24
    elligent
    -0.24
    POSITIVE LOGITS
    äºĴ
    0.28
    äºĴ缸
    0.28
    ä¸īæĸ¹
    0.26
    steen
    0.26
    -collapse
    0.26
    kap
    0.25
    cap
    0.25
     Kap
    0.25
     licking
    0.24
    å§ĵ
    0.24
    Activations Density 23.565%

    No Known Activations