© 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. 96107
    Prev
    Next
    INDEX
    Explanations

    Chinese language/location

    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
    Not in Any Lists

    No Comments

    Negative Logits
    é£İ鼨
    -0.30
    hart
    -0.27
    æ¡ĥèĬ±
    -0.27
    鹬
    -0.27
    ØŃاÙĨ
    -0.26
     season
    -0.26
     weather
    -0.26
     present
    -0.25
     turbulence
    -0.25
    ÑĤиÑĢ
    -0.25
    POSITIVE LOGITS
    ogne
    0.28
    ạp
    0.27
    agra
    0.26
    æıIJä¾Ľä¼ĺè´¨
    0.25
    wordpress
    0.25
    è§Ĵ
    0.25
    ä½ľåĵģåĨħ容
    0.25
    _ACC
    0.24
    é¢Ī
    0.24
     Corner
    0.24
    Activations Density 0.105%

    No Known Activations