© 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. 64822
    Prev
    Next
    INDEX
    Explanations

    ways manner

    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
    å¾Ĺèµ·
    -0.07
    _FOUND
    -0.06
    çĶŁç´ł
    -0.06
    è¿Ļéĥ¨åĪĨ
    -0.06
    è¡ĮåĬ¨è®¡åĪĴ
    -0.06
    è¿ĩå¤ļçļĦ
    -0.06
    berger
    -0.06
     instead
    -0.06
    اÙħØ©
    -0.06
    ç»ĪçĶŁ
    -0.06
    POSITIVE LOGITS
     Weise
    0.15
     ways
    0.13
    æĸ¹å¼ıè¿Ľè¡Į
    0.13
    æĸ¹å¼ıåĴĮ
    0.13
     cách
    0.13
    æĸ¹å¼ı
    0.13
     way
    0.12
     manière
    0.12
     manera
    0.12
     manner
    0.12
    Activations Density 0.334%

    No Known Activations