© 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. 15947
    Prev
    Next
    INDEX
    Explanations

    enabled optimization

    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
    arna
    -0.08
    маÑĤо
    -0.07
    æľĢæľī
    -0.07
    uito
    -0.07
    (IF
    -0.07
    ä½İçĤ¹
    -0.07
    ãģĭãĤĤãģĹãĤĮãģªãģĦ
    -0.07
    éta
    -0.06
    uart
    -0.06
     Kỳ
    -0.06
    POSITIVE LOGITS
    çļĦåīįæıIJä¸ĭ
    0.07
    åīįæıIJä¸ĭ
    0.07
    ä¸įæIJŀ
    0.07
    ahn
    0.07
    çļĦè¯Ŀ
    0.07
     Ñģоли
    0.07
    å±Ĭ
    0.07
     decent
    0.07
    çļĦä»Ĭ天
    0.07
    pack
    0.06
    Activations Density 0.081%

    No Known Activations