© 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. 7529
    Prev
    Next
    INDEX
    Explanations

    events and places

    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
    çĻ»è®°è¯ģ
    -0.07
    æĪIJæ´»
    -0.07
    æ¯ıå¹´éĥ½
    -0.07
    éĢIJå¹´
    -0.07
    æ¯ıåŃ£åº¦
    -0.07
    atives
    -0.07
    æ¯ıå¹´çļĦ
    -0.06
    nur
    -0.06
    éĢļ常为
    -0.06
    å²ģæŶ
    -0.06
    POSITIVE LOGITS
     recent
    0.11
     unprecedented
    0.10
     kemarin
    0.10
     recently
    0.09
     recente
    0.09
     récent
    0.09
    漩
    0.09
    recent
    0.09
     recenti
    0.09
    äºĭ件ä¸Ń
    0.09
    Activations Density 1.809%

    No Known Activations