© 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. 33383
    Prev
    Next
    INDEX
    Explanations

    parentheses and commas

    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
    /license
    -0.09
    ãģĻãģĻ
    -0.08
    amah
    -0.08
    irage
    -0.07
    带好
    -0.07
    丽ä¸Ŀ
    -0.07
    ç»ı审çIJĨæŁ¥æĺİ
    -0.07
    麦å½ĵ
    -0.07
    обÑĢази
    -0.07
    clud
    -0.07
    POSITIVE LOGITS
     bung
    0.07
    ä½Ļ项
    0.07
    æĪĸå°ij
    0.07
    -extra
    0.06
    æľªå®ĮæĪIJ
    0.06
     pcb
    0.06
    åĪ°åĵªéĩĮ
    0.06
    çĥ
    0.06
    eyer
    0.06
    æijĦ
    0.06
    Activations Density 0.002%

    No Known Activations