© 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. 29351
    Prev
    Next
    INDEX
    Explanations

    NOT value?

    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
    æ´»çļĦ
    -0.08
    ardo
    -0.07
    ')['
    -0.07
     parlam
    -0.07
    mens
    -0.07
    erable
    -0.07
    mse
    -0.07
    ικο
    -0.07
    èĶ¼
    -0.07
    ãģĹãĤĩãģĨ
    -0.07
    POSITIVE LOGITS
    éĢī项ä¸Ń
    0.12
     option
    0.10
    éĢī项
    0.10
     Option
    0.09
     options
    0.09
    ä¸ĭåĪĹ
    0.09
    éģ¸éłħ
    0.09
    åĵªä¸Ģ个
    0.09
     among
    0.09
    ä¸ĭè¿°
    0.08
    Activations Density 0.043%

    No Known Activations