© 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. 12680
    Prev
    Next
    INDEX
    Explanations

    white OLEDs

    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
    ÙĬتÙĬÙĨ
    -0.07
    ÙĪاÙħ
    -0.07
    æ¡Ī件éĢĤçĶ¨æ³ķå¾ĭ
    -0.07
    æĬ«
    -0.07
    onia
    -0.06
    tha
    -0.06
    èĭ±æĸĩåIJįåŃĹ
    -0.06
    wrapped
    -0.06
    ele
    -0.06
    çĶ°
    -0.06
    POSITIVE LOGITS
    æķ´ä½ĵä¸Ĭ
    0.09
    æķ´ä½ĵçļĦ
    0.09
     overall
    0.09
    çļĦåħ¶ä»ĸ
    0.08
    ÏĦÎŃÏģ
    0.08
     insgesamt
    0.08
    overall
    0.08
    artner
    0.08
    åħ¶ä½Ļ
    0.08
     demás
    0.07
    Activations Density 0.157%

    No Known Activations