© 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. 22828
    Prev
    Next
    INDEX
    Explanations

    importing python modules

    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
    oland
    -0.08
     convite
    -0.08
    ¾
    -0.08
    ä¸ĩä¸ĩ
    -0.08
     today
    -0.07
    ä¸įä¿Ĺ
    -0.07
     tonight
    -0.07
    ä¸įå¿į
    -0.07
    ansion
    -0.07
    çļĦä»Ĭ天
    -0.07
    POSITIVE LOGITS
    æľīçĪ±
    0.06
    ored
    0.06
    ä½Ĩä¸įéĻIJäºİ
    0.06
    tle
    0.06
    å¼¹
    0.06
    å¿ĥæĥĬ
    0.06
    çŃĿ
    0.06
    ADOR
    0.06
    æ£ĭ
    0.06
     sol
    0.06
    Activations Density 0.003%

    No Known Activations