© 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. 65365
    Prev
    Next
    INDEX
    Explanations

    prime factors or length

    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
    phia
    -0.07
    è¿Ŀåıįä¸Ĭè¿°
    -0.07
    urio
    -0.07
    raw
    -0.06
    aily
    -0.06
    æ¢Ĺ
    -0.06
    西游
    -0.06
    _secure
    -0.06
     downright
    -0.06
    é£İæ°´
    -0.06
    POSITIVE LOGITS
     |_|
    0.08
    åIJįåī¯åħ¶å®ŀ
    0.07
    çİĩè¾¾
    0.07
    bidden
    0.07
    ableView
    0.07
    ä¿¡æģ¯ç§ijæĬĢæľīéĻIJåħ¬åı¸
    0.07
    quette
    0.07
    大计
    0.07
    -services
    0.07
    è°ĭåĪĴ
    0.07
    Activations Density 0.007%

    No Known Activations