© 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. 34539
    Prev
    Next
    INDEX
    Explanations

    search warrant

    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
    ä¸İæľ¬ç½ij
    -0.08
    æ¼Ĥ
    -0.08
     ÑĢаÑģпÑĢед
    -0.08
    声æĺİèĢħ
    -0.08
    gnore
    -0.07
    ä½ij
    -0.07
    erator
    -0.07
     Survivor
    -0.07
    æĶ¾çĸĹ
    -0.07
    åݻ认è¯ģ
    -0.07
    POSITIVE LOGITS
    æī£æĬ¼
    0.11
    æIJľæŁ¥
    0.10
     lawful
    0.09
     warrant
    0.08
    éĢ®æįķ
    0.08
    åIJĪæ³ķçļĦ
    0.08
    æī£çķĻ
    0.08
    æĭĺ
    0.08
    å½ĵåľº
    0.08
    å½ĵéĿ¢
    0.08
    Activations Density 0.112%

    No Known Activations