© 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. 30-TRANSCODER-HP
    7. 95175
    Prev
    Next
    INDEX
    Explanations

    Miscellaneous news snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åŃ°
    -0.27
     physically
    -0.26
     sharing
    -0.26
    /projects
    -0.25
     consent
    -0.25
    ucs
    -0.25
    çħ§æĺİ
    -0.25
     cris
    -0.25
    .Permission
    -0.25
    ennon
    -0.25
    POSITIVE LOGITS
    åĿij
    0.38
     pits
    0.32
    åľ°ä¸Ń
    0.30
    -found
    0.30
     dun
    0.29
     caves
    0.29
    éģĹ
    0.28
    ockets
    0.28
    æ²īæ·Ģ
    0.28
     sediment
    0.28
    Activations Density 0.886%

    No Known Activations