© 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. 62925
    Prev
    Next
    INDEX
    Explanations

    share

    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
    Not in Any Lists

    No Comments

    Negative Logits
    è´Ŀå°Ķ
    -0.27
    lig
    -0.26
     cooperate
    -0.26
    æģ°æģ°
    -0.25
    land
    -0.25
    coop
    -0.24
     ia
    -0.24
    éħįåIJĪ
    -0.24
     Bell
    -0.24
     bell
    -0.24
    POSITIVE LOGITS
    arda
    0.30
    åħ¬åŃIJ
    0.26
    æĽ´æĸ°
    0.26
     kul
    0.26
     onClose
    0.25
    kul
    0.25
    ebin
    0.25
     СообÑī
    0.23
    骸
    0.23
    coder
    0.23
    Activations Density 5.249%

    No Known Activations