© 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. 27-TRANSCODER-HP
    7. 58466
    Prev
    Next
    INDEX
    Explanations

    technical text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è°¥
    -0.28
     inherited
    -0.28
    akedown
    -0.26
    èĢħçļĦ
    -0.26
    èĩ
    -0.26
    uzzy
    -0.25
    åľ¨åŃ¦æł¡
    -0.25
    éļ°
    -0.24
    çĸ¤
    -0.24
    æł¡åıĭ
    -0.24
    POSITIVE LOGITS
    åľ°çIJĨ
    0.26
    ainen
    0.26
    iran
    0.26
     automation
    0.25
    ','-
    0.25
     Staples
    0.25
    ield
    0.25
     ;;↵
    0.24
     `[
    0.24
     uten
    0.24
    Activations Density 1.025%

    No Known Activations