© 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. 31935
    Prev
    Next
    INDEX
    Explanations

    dates ending in GMT

    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
    éĿ©
    -0.07
    å½ĵæŶ
    -0.07
    å½ĵæŶçļĦ
    -0.07
    åı²
    -0.07
    ä¸Ģå¤ķ
    -0.06
    åIJİéĿ¢çļĦ
    -0.06
    éĤ£æ®µ
    -0.06
    ories
    -0.06
    iw
    -0.06
    æŁĵèī²
    -0.06
    POSITIVE LOGITS
    endis
    0.08
    иÑĤаÑĤÑĮ
    0.07
     Beri
    0.07
    euw
    0.07
    æĤ¨å½ĵåīįçļĦä½įç½®
    0.07
    inken
    0.07
    æĦŁåįģ足
    0.07
    å°ı天
    0.07
    .sul
    0.07
    è¦ĥ
    0.07
    Activations Density 0.035%

    No Known Activations