© 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. 8118
    Prev
    Next
    INDEX
    Explanations

    main part of the

    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
    aus
    -0.08
    ä¸į失
    -0.07
    åħ·æľīéĩįè¦ģçļĦ
    -0.07
     vorba
    -0.06
    lenia
    -0.06
    ä¸ĢåĪĻ
    -0.06
    æ½
    -0.06
    lias
    -0.06
    çļĦéĩįè¦ģæĢ§åĴĮ
    -0.06
    æŃ£åĽłä¸º
    -0.06
    POSITIVE LOGITS
    illas
    0.10
    驱åĬ¨åĬĽ
    0.08
    çİĭéģĵ
    0.08
    主è¯Ń
    0.08
    iew
    0.08
    imary
    0.08
    çªģçł´åı£
    0.07
    äºĨä¸ĢåĪĩ
    0.07
    æºIJæ³ī
    0.07
     primary
    0.07
    Activations Density 0.342%

    No Known Activations