© 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. 9803
    Prev
    Next
    INDEX
    Explanations

    exceed or meet a threshold

    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
    èĩªç¼ĸ
    -0.07
    å°½éĩıéĢīæĭ©
    -0.07
    对ä¸įåIJĮ
    -0.07
    rach
    -0.07
    èĩªæĪij管çIJĨ
    -0.07
    ë¡Ŀ
    -0.07
    áĥIJáĥĻ
    -0.07
    ä¸İæľ¬
    -0.07
    cker
    -0.07
     daÃŃ
    -0.07
    POSITIVE LOGITS
    ä¸ĢåĪĩçļĦ
    0.08
    åħ¶æīĢ
    0.08
     ever
    0.07
    zum
    0.07
    æĪijæĦ¿
    0.07
    æīĢèĥ½
    0.06
    ä¸ĢåĪĩ
    0.06
    æŶ令
    0.06
    _thresh
    0.06
    ä¸ĢçŃ¹
    0.06
    Activations Density 0.024%

    No Known Activations