© 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. 9774
    Prev
    Next
    INDEX
    Explanations

    code definitions `def` or `class`

    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
    endorf
    -0.10
    ä¹ĭæĢ¥
    -0.08
    ãĥ«ãĥķ
    -0.08
    oret
    -0.07
    obra
    -0.07
     INTROD
    -0.07
    arang
    -0.07
     thoại
    -0.07
    ulen
    -0.07
    gaz
    -0.07
    POSITIVE LOGITS
    ä¸Ķ
    0.07
    aign
    0.07
    Ỽn
    0.07
    ÃŃss
    0.06
    ependency
    0.06
    èĢĮåıĪ
    0.06
    浩浩
    0.06
    ãģĭãģ¤
    0.06
    æīĵæŃ»
    0.06
    åĴĮåľ¨
    0.06
    Activations Density 0.136%

    No Known Activations