© 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. 29635
    Prev
    Next
    INDEX
    Explanations

    nth smallest or biggest 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
    erner
    -0.08
    ibes
    -0.07
    éĵ¸
    -0.07
    è¡į
    -0.07
    ieres
    -0.07
    æģ¤
    -0.07
    åĪĨå±ħ
    -0.07
    ׾×IJ
    -0.07
    Emb
    -0.07
    ä¸Ģè¨Ģ
    -0.07
    POSITIVE LOGITS
    à¹Ģà¸Ħ
    0.09
    _nth
    0.08
    nth
    0.08
    åĴĮ第
    0.07
    ä½įç½®ä¸Ĭ
    0.07
     Cush
    0.07
     ë²Ī째
    0.07
    odash
    0.07
    ë²Ī째
    0.07
    mite
    0.07
    Activations Density 0.033%

    No Known Activations