© 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. 3136
    Prev
    Next
    INDEX
    Explanations

    price indications

    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
    æĬ±ä½ı
    -0.07
    amas
    -0.07
    iloc
    -0.07
    èĻı
    -0.06
    rollo
    -0.06
    æ³£
    -0.06
    è¿ľ
    -0.06
    å¼Ģæ°´
    -0.06
    åĢĴ
    -0.06
    asco
    -0.06
    POSITIVE LOGITS
    çķ¥å¾®
    0.09
    çķ¥
    0.09
     slightly
    0.08
    biet
    0.08
    çķ¥æľī
    0.08
    微微
    0.08
    ÑģÑģоÑĢа
    0.08
    æľ¬ç½ij
    0.07
    hér
    0.07
    afen
    0.07
    Activations Density 0.010%

    No Known Activations