© 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. 44128
    Prev
    Next
    INDEX
    Explanations

    repulsion or feedback

    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
    ä¼ı
    -0.08
     Receiver
    -0.07
    æļĹæ·¡
    -0.07
    褪
    -0.07
    éĻįåĪ°
    -0.07
     Down
    -0.07
    转移åĪ°
    -0.06
    æ´ŀéĩĮ
    -0.06
    èĪįå¾Ĺ
    -0.06
    èIJ¤çģ«
    -0.06
    POSITIVE LOGITS
    éĺ»æŃ¢
    0.14
    éĺ²æŃ¢
    0.13
     preventing
    0.11
    æĴij
    0.11
    ä¿ĿèŃ·
    0.11
     пÑĢепÑıÑĤ
    0.11
    åĪ¶æŃ¢
    0.11
    ä¿ĿæĬ¤
    0.11
     protective
    0.10
    éĺ»æĮ¡
    0.10
    Activations Density 0.044%

    No Known Activations