© 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. 41476
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions as latex

    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
    å°ĶèĴĻ
    -0.07
    upa
    -0.07
    -fit
    -0.07
     eyl
    -0.07
     existed
    -0.07
    æĸ°åħµ
    -0.07
    å¦ĸåŃ½
    -0.07
    umpa
    -0.07
    ÑĤÑģÑı
    -0.07
    elib
    -0.07
    POSITIVE LOGITS
    kana
    0.07
    boxed
    0.07
    åı¯ä¸į
    0.07
    блÑĸ
    0.06
    mast
    0.06
    hec
    0.06
    arest
    0.06
    综ä¸ĬæīĢè¿°
    0.06
    baden
    0.06
    vl
    0.06
    Activations Density 0.001%

    No Known Activations