© 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. 7460
    Prev
    Next
    INDEX
    Explanations

    spite, doubt, sooner, definitely

    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
    åĴļåĴļ
    -0.08
    irman
    -0.08
    ä¸įåı¯æĢĿè®®
    -0.08
    ober
    -0.08
    ÑĩеÑģ
    -0.07
    ocking
    -0.07
    ç»ıæŁ¥
    -0.07
    scribe
    -0.07
    çļĦäººä¹Ł
    -0.07
    igna
    -0.07
    POSITIVE LOGITS
    Ìģ
    0.07
    ä¹İåħ¶
    0.07
    pron
    0.06
    iht
    0.06
    åĮ»ç§ij大åѦéĻĦå±ŀ
    0.06
    è¯Ńæ°Ķ
    0.06
    ạt
    0.06
    /
    0.06
     (=
    0.06
    æĺ¾å¾Ĺ
    0.06
    Activations Density 0.123%

    No Known Activations