© 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. 62833
    Prev
    Next
    INDEX
    Explanations

    programming, math, file paths

    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
    åıĸå¾Ĺ
    -0.27
    å®ıè§Ĥ
    -0.26
     immedi
    -0.24
    å®ĹæķĻ
    -0.24
    ERIC
    -0.24
    çĪ½
    -0.24
    åIJİèĢħ
    -0.24
    æ¹Ķ
    -0.23
     socio
    -0.23
     DY
    -0.23
    POSITIVE LOGITS
     translating
    0.26
    Measured
    0.25
     Bew
    0.24
    gue
    0.24
     pockets
    0.24
    abcdefgh
    0.23
     buying
    0.23
    åIJĮåŁİ
    0.23
    Advertisements
    0.23
    (pm
    0.23
    Activations Density 17.616%

    No Known Activations