© 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. 28778
    Prev
    Next
    INDEX
    Explanations

    our technicians

    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
    æľīçĶŁ
    -0.08
    åİ¥
    -0.07
    è²Į
    -0.07
     auÃŁer
    -0.06
    é¢
    -0.06
    ammer
    -0.06
    æĹ©éĢŁ
    -0.06
    çķ¥
    -0.06
    elok
    -0.06
    Marks
    -0.06
    POSITIVE LOGITS
     inoltre
    0.08
    çĶļèĩ³åľ¨
    0.08
    ç½ijç«Ļåľ°åĽ¾
    0.08
    åį³ä½¿æĺ¯
    0.07
    çĶļèĩ³è¿ĺ
    0.07
    ä¹ŁæĽ´åĬł
    0.07
     ìĭ¬ì§Ģìĸ´
    0.07
    ubile
    0.07
    çĶļèĩ³äºİ
    0.07
    åľ¨ä¸ĢäºĽ
    0.07
    Activations Density 0.049%

    No Known Activations