© 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. 28092
    Prev
    Next
    INDEX
    Explanations

    Let Suppose

    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
     Ñģанк
    -0.07
    hut
    -0.07
    unti
    -0.07
    uruh
    -0.07
    éļĶ天
    -0.07
    ê±´
    -0.07
    æ²»çĸĹçļĦ
    -0.07
    æĽ´æĸ°æŶéĹ´
    -0.07
    äºĶ代
    -0.07
    isiones
    -0.07
    POSITIVE LOGITS
    urs
    0.07
     Eure
    0.07
    æīĢåIJ¸å¼ķ
    0.07
    iet
    0.07
    aus
    0.06
    è¢«ä½ł
    0.06
    Fo
    0.06
    äºĮè¿ŀ
    0.06
     pull
    0.06
     eo
    0.06
    Activations Density 0.124%

    No Known Activations