© 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. 34521
    Prev
    Next
    INDEX
    Explanations

    explaining or describing texts

    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
    å½ĵæŶ
    -0.09
    å½ĵæŶçļĦ
    -0.08
     probable
    -0.07
    éĤ£æŶåĢĻ
    -0.07
    Prob
    -0.07
    è®°ä½ıäºĨ
    -0.07
     damals
    -0.07
     Prob
    -0.07
    çķ¶æĻĤ
    -0.07
    برة
    -0.07
    POSITIVE LOGITS
    instanc
    0.09
    æĹĹé¼ĵ
    0.08
    ؤÙĦ
    0.08
    ستاذ
    0.07
    “Our
    0.07
    ÙĨÙĪاÙĨ
    0.07
     admittedly
    0.07
    éĢģæĪij
    0.07
    icka
    0.07
    mdir
    0.07
    Activations Density 0.373%

    No Known Activations