© 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. 10789
    Prev
    Next
    INDEX
    Explanations

    closing punctuation or bracket

    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
    å¤©çľ¼
    -0.08
    ément
    -0.08
    ingham
    -0.07
     paixão
    -0.07
    ↵        ↵        ↵
    -0.07
    igation
    -0.07
    ↵    ↵    ↵
    -0.07
    ation
    -0.07
     ".$_
    -0.07
    leck
    -0.07
    POSITIVE LOGITS
    äch
    0.08
    stry
    0.07
     cst
    0.07
    åħħåĪĨä½ĵçİ°
    0.06
    ixe
    0.06
    hs
    0.06
    etra
    0.06
    æ°ijæĹıçļĦ
    0.06
    说çļĦè¯Ŀ
    0.06
    åħ¶ä¸Ń
    0.06
    Activations Density 0.001%

    No Known Activations