© 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. 10402
    Prev
    Next
    INDEX
    Explanations

    explicitly or manually

    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
    èī°
    -0.07
    æ¼Ĥ
    -0.07
    Ïģαί
    -0.07
     arity
    -0.06
    akis
    -0.06
    ocat
    -0.06
     ÑģÑĭ
    -0.06
    losion
    -0.06
    ç¾ģ
    -0.06
    ç¼ĸç¨ĭ
    -0.06
    POSITIVE LOGITS
    çĽ¸çº¦
    0.08
    åľ°ä¸ĭ
    0.08
    æĪijæ¯ı天
    0.07
    Äħż
    0.07
    åĵģçīĮæݨ广
    0.07
    lese
    0.07
    Scheduled
    0.07
     underground
    0.07
    INET
    0.07
    posting
    0.06
    Activations Density 0.001%

    No Known Activations