© 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. 49915
    Prev
    Next
    INDEX
    Explanations

    names and roles

    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
    zyw
    -0.07
    ãģĻãĤĭãģĵãģ¨ãģĮ
    -0.06
    2
    -0.06
    tee
    -0.06
    ement
    -0.06
    rod
    -0.06
    å°±æĺ¯
    -0.06
    iform
    -0.06
    ament
    -0.06
    æī¿æĭħä¸ĢåĪĩ
    -0.06
    POSITIVE LOGITS
    çŃīåħ¶ä»ĸ
    0.08
    dessen
    0.08
    yyÉĻ
    0.07
    æŁ»
    0.07
    ransition
    0.07
    çŃīä¼Ĺå¤ļ
    0.07
     uploader
    0.07
    .numpy
    0.07
    UGIN
    0.07
    anners
    0.07
    Activations Density 0.042%

    No Known Activations