© 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. 58679
    Prev
    Next
    INDEX
    Explanations

    copyright

    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
     Runtime
    -0.07
     neg
    -0.07
    ERTO
    -0.07
    è¿Ľåħ¥æ¸¸æĪı
    -0.07
    éĩĮæĸ¯
    -0.07
     Shops
    -0.07
    psilon
    -0.07
    erta
    -0.07
    好åij¢
    -0.07
    borg
    -0.07
    POSITIVE LOGITS
    atismo
    0.08
    assin
    0.08
    ijd
    0.07
    æ±Łå±±
    0.07
    æħ·
    0.07
     ][
    0.06
    åħ¶ä»ĸ人
    0.06
    ctions
    0.06
    ãĥªãĥ¼ãĤ°
    0.06
    æĸ°æ¦Ĥ念
    0.06
    Activations Density 0.016%

    No Known Activations