© 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. 2503
    Prev
    Next
    INDEX
    Explanations

    or and

    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
    chor
    -0.07
    ä¸Ĭè¿Ľ
    -0.07
    byg
    -0.06
    éĹŃå¡ŀ
    -0.06
    Ùĩا
    -0.06
    REL
    -0.06
    Ø·ÙĤ
    -0.06
    人åİ»
    -0.06
    èĩªç§ģ
    -0.06
    鼷éĶĭ
    -0.06
    POSITIVE LOGITS
    çŃīåħ¶ä»ĸ
    0.12
     tháºŃm
    0.10
     sogar
    0.09
     ìĭ¬ì§Ģìĸ´
    0.09
     tampoco
    0.09
    çĶļèĩ³
    0.09
     even
    0.09
    çĶļèĩ³åľ¨
    0.09
    çĶļèĩ³æĺ¯
    0.08
    çĶļèĩ³è¿ĺ
    0.08
    Activations Density 0.238%

    No Known Activations