© 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. 48541
    Prev
    Next
    INDEX
    Explanations

    question or statement transition

    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
    å¼¹
    -0.08
     Giac
    -0.07
    ạ
    -0.07
    adem
    -0.06
    Preference
    -0.06
    zzo
    -0.06
    ä¸įçŁ¥ä¸įè§ī
    -0.06
    éĢļè¿ĩè¿ĻäºĽ
    -0.06
    atisfaction
    -0.06
    ÐŁÑĢа
    -0.06
    POSITIVE LOGITS
     anyway
    0.09
    ä¾Ŀæŧæĺ¯
    0.08
     anyways
    0.08
    ä¸į管æĢİæł·
    0.08
     sublic
    0.08
    æĹ¢çĦ¶æĺ¯
    0.08
     whichever
    0.08
    ä¾ĿçĦ¶æĺ¯
    0.08
    åį³ä¾¿å¦ĤæѤ
    0.08
    дев
    0.08
    Activations Density 0.057%

    No Known Activations