© 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. 18132
    Prev
    Next
    INDEX
    Explanations

    hint and keywords

    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
    ouis
    -0.08
    oter
    -0.08
    ä»İæĹł
    -0.08
    ampir
    -0.07
    ä¸ĭè½½æĬ¥åijĬ
    -0.07
    éģµå®ĪåĽ½å®¶
    -0.07
    éķ¿åĪ¶
    -0.07
    £¼
    -0.07
    è´Łèį·
    -0.07
    äºijé£ŀ
    -0.07
    POSITIVE LOGITS
    解åĨ³éĹ®é¢ĺçļĦ
    0.08
     algebra
    0.08
    å°ıé¢ĺ
    0.07
    åİŁé¢ĺ
    0.07
    èĮĹ
    0.07
     geometric
    0.06
    æݢ究
    0.06
    еÑĢна
    0.06
    å¹Ĥ
    0.06
    ç´łåħ»
    0.06
    Activations Density 0.002%

    No Known Activations