© 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. 982
    Prev
    Next
    INDEX
    Explanations

    method, query, argues, repairs, understand

    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
    ç´¢æĢ§
    -0.08
    perto
    -0.08
    ä»Ĭ天å°ıç¼ĸ
    -0.08
    æīįè¡Į
    -0.07
     deserved
    -0.07
    wai
    -0.07
    æľīæīĢ
    -0.07
    occo
    -0.07
    鹿æĻĹ
    -0.07
    pery
    -0.07
    POSITIVE LOGITS
    对åħ¶è¿Ľè¡Į
    0.14
    对è¿ĻäºĽ
    0.14
    ä¸İä¹ĭ
    0.12
    åľ¨è¿Ļæł·çļĦ
    0.12
    对è¿Ļ个
    0.12
    对æѤ
    0.12
    对该
    0.11
    åľ¨è¿ĻäºĽ
    0.11
    å°Ĩè¿ĻäºĽ
    0.11
    å°Ĩè¿Ļ个
    0.11
    Activations Density 0.900%

    No Known Activations