© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21703
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives

    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
    御åı²
    -0.07
     ÑģÑĤÑĢого
    -0.07
     wes
    -0.07
    æ¯Ķ以å¾Ģ
    -0.06
    æ¡ĥæĿİ
    -0.06
    严éĩį
    -0.06
    å®Įåħ¨
    -0.06
    гүй
    -0.06
    å®Įåħ¨ãģ«
    -0.06
    临æŶ
    -0.06
    POSITIVE LOGITS
    å°±è¶Ĭ
    0.12
    åıįä¹ĭ
    0.12
     desto
    0.11
    è¶Ĭ好
    0.10
    èİ·å¾ĹæĽ´å¤ļçļĦ
    0.10
    è¶Ĭ强
    0.09
    è¶Ĭæĺ¯
    0.09
    è¶Ĭé«ĺ
    0.09
    ìĪĺë¡Ŀ
    0.09
     vice
    0.09
    Activations Density 0.036%

    No Known Activations