© 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. 25496
    Prev
    Next
    INDEX
    Explanations

    question or code snippet

    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
    æĪijåıªå¥½
    -0.08
    æĹłåı¯å¥Īä½ķ
    -0.08
    uhl
    -0.07
    西山
    -0.07
    幡
    -0.07
    æī¶
    -0.07
    ä¸įéĩįè¦ģ
    -0.07
    utdown
    -0.07
    izzo
    -0.07
    å®ģæĦ¿
    -0.07
    POSITIVE LOGITS
    å®Įç¾İçļĦ
    0.07
    åºĶ该注æĦı
    0.07
    æīĢ使çĶ¨çļĦ
    0.07
     flawless
    0.07
     ê³¼ìĹ°
    0.07
    å®Įå¤ĩ
    0.06
    eder
    0.06
    é½IJåħ¨çļĦ
    0.06
    åĩºçİ°çļĦéĹ®é¢ĺ
    0.06
    ä¸ĢäºĽéĹ®é¢ĺ
    0.06
    Activations Density 0.174%

    No Known Activations