© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 96165
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    绣
    -0.25
     Trafford
    -0.25
     bubble
    -0.25
     live
    -0.25
     Learned
    -0.24
    åľ°çĭ±
    -0.24
    .Google
    -0.24
     google
    -0.24
    tha
    -0.23
    óg
    -0.23
    POSITIVE LOGITS
    ä¼ģä¸ļåĴĮ
    0.28
    \Active
    0.27
    arts
    0.26
    æľ¬ç«Ļ
    0.25
    umer
    0.25
    èµ°å¾Ĺ
    0.25
    ded
    0.24
    éĵĹ
    0.24
    sup
    0.24
     CAL
    0.23
    Activations Density 0.882%

    No Known Activations

    This feature has no known activations.