© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 40979
    Prev
    Next
    INDEX
    Explanations

    haiku and poetry

    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
    éŁ³æłĩ
    -0.07
    补课
    -0.07
    æ¼ĶçļĦ
    -0.07
    ç¾İåī§
    -0.07
    泡
    -0.07
    èݱåĿŀ
    -0.06
    isRequired
    -0.06
    æĵįä½ľ
    -0.06
    éħįéŁ³
    -0.06
    achs
    -0.06
    POSITIVE LOGITS
    æĦıå¢ĥ
    0.12
    è¯Ĺ人
    0.10
    è¿Ļé¦ĸè¯Ĺ
    0.10
    åĴı
    0.10
    ç¾ģ
    0.09
    è¯Ĺåı¥
    0.09
    è¯Ĺ
    0.09
    çİĭç»´
    0.09
     poem
    0.09
    è¯Ĺä¸Ń
    0.08
    Activations Density 0.002%

    No Known Activations