© 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. 37831
    Prev
    Next
    INDEX
    Explanations

    driver, exception, fat, pass, lines, javascript, mail

    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
    íij¸
    -0.08
    RequestMethod
    -0.08
    tesi
    -0.08
    对ä¸Ĭè¿°
    -0.08
     sortes
    -0.08
    ansir
    -0.07
    resso
    -0.07
    positor
    -0.07
    elp
    -0.07
    hati
    -0.07
    POSITIVE LOGITS
    è¯
    0.06
    æĪİ
    0.06
    åĽºçĦ¶
    0.06
    اء
    0.06
    çļĦåīįæıIJä¸ĭ
    0.06
    ��
    0.06
    çĦ¶åIJİ
    0.06
     [âĢ¦]
    0.06
    ·
    0.05
     *(
    0.05
    Activations Density 0.129%

    No Known Activations