© 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. 58058
    Prev
    Next
    INDEX
    Explanations

    best, safest, unlikely

    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
    दà¥įर
    -0.08
    /--
    -0.08
    igham
    -0.08
    -&
    -0.08
    å±ĪæĮĩ
    -0.07
    į¼
    -0.07
    以ä¸ĭåĩł
    -0.07
    éĤ£ç§į
    -0.07
    APPED
    -0.07
    çī¹æѤ
    -0.07
    POSITIVE LOGITS
    éĤ£å°±æĺ¯
    0.08
    obook
    0.07
     yaitu
    0.07
    ì²´ìĿ¸
    0.07
    åį³
    0.07
     =
    0.07
    ogue
    0.07
    ä¹īçļĦ
    0.06
    书çļĦ
    0.06
     namely
    0.06
    Activations Density 0.014%

    No Known Activations