© 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. 57972
    Prev
    Next
    INDEX
    Explanations

    phrases ending with punctuation or list items

    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
     interpretation
    -0.08
    å¦Īå¦Ī说
    -0.07
    æĬĹæ´ª
    -0.07
    unce
    -0.07
    Ø®ÙĪر
    -0.07
    oord
    -0.07
    åĭ¿æī°
    -0.07
    åĬłæ·±å¯¹
    -0.07
    ieu
    -0.07
    注æĦıçĤ¹
    -0.07
    POSITIVE LOGITS
    幸
    0.07
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    0.07
     numbered
    0.07
    ÄĻ
    0.07
    éĩıåĮĸ
    0.07
    ä¸ĭå®ļ
    0.07
    馨
    0.06
     заÑħо
    0.06
    ä¸ĢæĿ¡æĿ¡
    0.06
    leta
    0.06
    Activations Density 0.013%

    No Known Activations