© 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. 97148
    Prev
    Next
    INDEX
    Explanations

    str

    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
    åĺĽ
    -0.27
    å¤§åľ°
    -0.25
    veal
    -0.24
    enade
    -0.24
    ury
    -0.24
    è¼ī
    -0.24
    åįĬ个
    -0.23
    -load
    -0.23
     UR
    -0.23
    ely
    -0.23
    POSITIVE LOGITS
     stretch
    0.35
     Stretch
    0.34
     Slayer
    0.31
    stretch
    0.30
     stretches
    0.29
    ainers
    0.28
    tracker
    0.27
    adders
    0.27
    sit
    0.27
    æĬĵæįķ
    0.27
    Activations Density 0.008%

    No Known Activations