© 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. 65192
    Prev
    Next
    INDEX
    Explanations

    nerve terminal, methyl group

    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
    åİ
    -0.08
     Spec
    -0.08
    çĪ±çļĦ人
    -0.07
    æŃ¤èµ·å½¼
    -0.07
    éĿĴæĿ¾
    -0.07
    åŁ
    -0.06
    izie
    -0.06
    _BIN
    -0.06
    éĺ²æļij
    -0.06
    åı°
    -0.06
    POSITIVE LOGITS
    åİŁæľ¬æĺ¯
    0.08
    ãĥĨãĥ¼
    0.08
    æİĮä¸Ĭ
    0.07
    igus
    0.07
    人æĿ¥è¯´
    0.07
     itulah
    0.07
    ['__
    0.07
    imea
    0.07
     originally
    0.07
    åĩºäºĨä¸Ģ个
    0.07
    Activations Density 0.006%

    No Known Activations