© 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. 45584
    Prev
    Next
    INDEX
    Explanations

    able to prove

    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
    éĩijé¦Ļ
    -0.09
    кок
    -0.08
    ä¸į欲
    -0.08
    бен
    -0.08
    è¡·å¿ĥçļĦ
    -0.07
    conto
    -0.07
    phins
    -0.07
     mód
    -0.07
    缸æī£
    -0.07
    ä»Ģä¹Īåij¢
    -0.07
    POSITIVE LOGITS
    ness
    0.08
    åĪ
    0.07
    heit
    0.07
    åĴĮä¸į
    0.07
    ity
    0.07
    ilinear
    0.06
     outright
    0.06
    izable
    0.06
    ie
    0.06
    ä¸Ķåľ¨
    0.06
    Activations Density 0.049%

    No Known Activations