© 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. 9512
    Prev
    Next
    INDEX
    Explanations

    quirky, customizable, innovation, talent

    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
    ä¾ĭå¦Ĥ
    -0.08
    åºĶå½ĵä¾Ŀçħ§
    -0.07
    æ¯Ķå¦Ĥ
    -0.07
    æ¯Ķå¦Ĥåľ¨
    -0.07
    å¦Ĥæ¶īåıĬ
    -0.07
    æīĢ以è¦ģ
    -0.07
    诸å¦Ĥ
    -0.07
    oder
    -0.06
    èѬå¦Ĥ
    -0.06
    以ä¸ĭåĩł
    -0.06
    POSITIVE LOGITS
    åıĪä¸Ģ个
    0.08
    éĹ´æİ¥
    0.08
     sekaligus
    0.08
    #index
    0.08
    宫å¤ĸ
    0.07
    ÃīM
    0.07
    åıĪä¸Ģ次
    0.07
     trec
    0.07
     INDIRECT
    0.07
     indirect
    0.07
    Activations Density 0.076%

    No Known Activations