© 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. 50588
    Prev
    Next
    INDEX
    Explanations

    part of something bigger

    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
     deta
    -0.08
    ä½łçļĦ人
    -0.08
    ((__
    -0.08
    stellen
    -0.07
    ä¸įæĸĻ
    -0.07
    زت
    -0.06
    landers
    -0.06
    çĭ±
    -0.06
    符åIJĪè¦ģæ±Ĥ
    -0.06
    reet
    -0.06
    POSITIVE LOGITS
    éĶĢåĶ®ç½ij绾
    0.08
    åIJĮä¸Ģ个
    0.07
    optgroup
    0.07
    Ùĥب
    0.07
    -packages
    0.07
    æĪĸ被
    0.07
     بÙĨدÛĮ
    0.07
    并被
    0.07
    æ¡ĥèĬ±
    0.07
    å¿«éĢĴåħ¬åı¸
    0.07
    Activations Density 0.171%

    No Known Activations