© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50015
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and assignments

    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
    çľĭä½ľ
    -0.08
    phia
    -0.07
    æ¯Ķä½ľ
    -0.07
    ilia
    -0.07
    å¼Ħå¾Ĺ
    -0.07
    带åĪ°äºĨ
    -0.07
     vastaan
    -0.07
    @",
    -0.07
    ãģ¨ãģĻãĤĭ
    -0.06
    ä½ľä¸ºä¸Ģ个
    -0.06
    POSITIVE LOGITS
    ãĢİ
    0.08
    æ¦Ħ
    0.08
    entu
    0.08
     SERVIZI
    0.07
    被åħ³éĹŃ
    0.07
    å°Ĩèĩªå·±çļĦ
    0.07
     ãĢİ
    0.07
    æ°´ä¸ĭ
    0.07
    ä¸Ńå°Ĩ
    0.07
    жиÑĤÑģÑı
    0.07
    Activations Density 0.175%

    No Known Activations