© 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. 11937
    Prev
    Next
    INDEX
    Explanations

    in [context/explanation]

    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
    éĥ¨èIJ½å®¢
    -0.08
    åIJ¦
    -0.07
    Debugger
    -0.07
     Legislat
    -0.07
    [js
    -0.07
    (Font
    -0.07
    :nil
    -0.07
    åħĪåľ¨
    -0.07
    çķĻåľ¨
    -0.07
    rå
    -0.07
    POSITIVE LOGITS
     discussions
    0.08
     context
    0.07
     early
    0.07
     terminology
    0.06
     practice
    0.06
    æŁIJç§įæĦıä¹īä¸Ĭ
    0.06
     اصط
    0.06
    å¾Īéķ¿ä¸Ģ段æŶéĹ´
    0.06
    ç»ĻåĩºçļĦ
    0.06
    ferences
    0.06
    Activations Density 0.044%

    No Known Activations