© 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. 131093
    Prev
    Next
    INDEX
    Explanations

    People's names/writings

    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
    hti
    -0.28
    ä»»ä½ķ人
    -0.25
     preamble
    -0.25
    纪æ£Ģ
    -0.25
    rawler
    -0.24
    wh
    -0.24
    oram
    -0.24
     movable
    -0.24
    _orient
    -0.24
     spokes
    -0.24
    POSITIVE LOGITS
    enburg
    0.28
    æ¯ķ
    0.27
    ç§ijå°Ķ
    0.25
    Pid
    0.25
    ün
    0.25
     cq
    0.25
     Heb
    0.25
    åĪ°æĿ¥
    0.24
    åħ«å¤§
    0.24
    ź
    0.24
    Activations Density 8.039%

    No Known Activations