© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 47337
    Prev
    Next
    INDEX
    Explanations

    short circuit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    neau
    -0.07
    iore
    -0.07
     ìĺ¬
    -0.07
     Kurd
    -0.07
    åŃĺéĩı
    -0.06
    åģľä¸ĭæĿ¥
    -0.06
    å§Ķ
    -0.06
    èĢĮçŁ¥
    -0.06
    æĽ´æĸ°çļĦ
    -0.06
    anis
    -0.06
    POSITIVE LOGITS
    æĶ¾çĶµ
    0.08
     bypass
    0.08
    éĢļè·¯
    0.08
    è¿ŀæİ¥
    0.08
     discharge
    0.08
    éĢļå¾Ģ
    0.08
    urrent
    0.07
    .connect
    0.07
    yin
    0.07
     Editor
    0.07
    Activations Density 0.016%

    No Known Activations