© 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. 21179
    Prev
    Next
    INDEX
    Explanations

    exceeding or greater than

    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
    ä¸į足以
    -0.08
    ä¸ĩå¹´
    -0.07
     Soll
    -0.07
    空èĻļ
    -0.07
     chmod
    -0.07
     slashed
    -0.07
     mysterious
    -0.07
    å¼±ãģĦ
    -0.06
    OfType
    -0.06
    èĴĻèĴĻ
    -0.06
    POSITIVE LOGITS
    è¶ħåĩºäºĨ
    0.17
    è¶ħåĩº
    0.15
    è¶ħè¿ĩäºĨ
    0.14
     exceeds
    0.13
     exceeding
    0.12
     exceed
    0.12
    è¶ħè¿ĩ
    0.12
    è¿ľè¶ħ
    0.11
    ä¸įèĥ½è¶ħè¿ĩ
    0.11
    å·²ç»ıè¶ħè¿ĩ
    0.11
    Activations Density 0.094%

    No Known Activations