© 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. 9784
    Prev
    Next
    INDEX
    Explanations

    increasingly + adjective/becoming

    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
    ç«ĭåį³
    -0.08
    ursor
    -0.08
    igua
    -0.07
    èĩ´æķ¬
    -0.07
    à¸ĵà¹Į
    -0.07
     trÆ°ng
    -0.07
    转载æĪĸ
    -0.07
    åĪļåĪ°
    -0.07
    大èĩ´
    -0.06
    à°³à±į
    -0.06
    POSITIVE LOGITS
    è¶ĬæĿ¥è¶Ĭå¤ļçļĦ
    0.18
    è¶ĬæĿ¥è¶Ĭ
    0.18
    è¶ĬæĿ¥è¶Ĭå¤ļ
    0.17
    ä¹Łè¶ĬæĿ¥è¶Ĭ
    0.17
     increasingly
    0.16
    è¶Ĭä¾Ĩè¶Ĭ
    0.16
    è¶ĬæĿ¥è¶Ĭå¤ļçļĦ人
    0.15
    è¶ĬæĿ¥è¶Ĭ大
    0.14
    æĦĪæĿ¥æĦĪ
    0.14
    è¶ĬæĿ¥è¶Ĭé«ĺ
    0.14
    Activations Density 0.523%

    No Known Activations