© 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. 14117
    Prev
    Next
    INDEX
    Explanations

    a list of items

    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
     greatest
    -0.07
    åĽ
    -0.07
    ToEnd
    -0.07
    linger
    -0.06
     dismissed
    -0.06
     someone
    -0.06
    upt
    -0.06
     nächste
    -0.06
    æŁIJä¸Ģ
    -0.06
     same
    -0.06
    POSITIVE LOGITS
    æŃ¢
    0.08
    ä½ľåĪĻ
    0.07
    opsis
    0.07
    为该
    0.07
    ảo
    0.07
    ë§ŀ
    0.07
    ython
    0.07
    anst
    0.07
    acon
    0.07
    ormal
    0.07
    Activations Density 0.387%

    No Known Activations