© 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. 32665
    Prev
    Next
    INDEX
    Explanations

    addressing or discussing

    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
     oneself
    -0.09
    åĽ¾çīĩæĪĸ
    -0.09
    ç»ĻåĪ«äºº
    -0.08
    æĪĸèĢħæĺ¯
    -0.08
    hoven
    -0.08
    å¤įåĪ¶æĪĸ
    -0.08
    ä¸įåºĶ该
    -0.08
     vagy
    -0.07
     либо
    -0.07
    å¾Ģå¾Ģæĺ¯
    -0.07
    POSITIVE LOGITS
     myself
    0.10
    æĪijèĩªå·±çļĦ
    0.09
    .):
    0.09
    å¦Ĥä¸ĭ
    0.08
     поÑģÑĤаÑĢа
    0.08
    åĬĽæ±Ĥ
    0.08
    å°½éĩı
    0.08
     based
    0.08
     cautiously
    0.08
    çĽ¡éĩı
    0.08
    Activations Density 0.042%

    No Known Activations