© 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. 25936
    Prev
    Next
    INDEX
    Explanations

    confusing or strange scenarios

    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
    éģŃåĪ°
    -0.07
    ukul
    -0.07
    æIJŃ
    -0.06
    /sl
    -0.06
    åºĶèĢĥèĻij
    -0.06
    kö
    -0.06
    æĭĸæĭī
    -0.06
    kreis
    -0.06
    活泼
    -0.06
    Esc
    -0.06
    POSITIVE LOGITS
    åIJįåī¯åħ¶å®ŀ
    0.10
    åIJįåī¯
    0.08
    reden
    0.08
    级以ä¸Ĭ
    0.08
    _passwd
    0.08
    èĬ±èĮ¶
    0.08
    Õ²
    0.08
    åIJįæĢĿ
    0.07
    ูà¸Ķ
    0.07
    pal
    0.07
    Activations Density 0.006%

    No Known Activations