© 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. 49200
    Prev
    Next
    INDEX
    Explanations

    numeric and symbolic sequences

    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
    åŁİå¤ĸ
    -0.07
    ability
    -0.07
    弯弯
    -0.06
    меÑĤо
    -0.06
    ÛķÙĪÛķ
    -0.06
    appa
    -0.06
    æĬĬä»ĸçļĦ
    -0.06
    wer
    -0.06
    è¶ĬæĿ¥è¶Ĭ
    -0.06
    ijen
    -0.06
    POSITIVE LOGITS
     Fertig
    0.08
    åĪ©çī©
    0.08
    abee
    0.07
    inous
    0.07
     lips
    0.07
     Vive
    0.07
    åIJ¼
    0.07
    åı«å¥½
    0.07
    ãĥªãĤ¹
    0.07
    æ¤į
    0.06
    Activations Density 0.005%

    No Known Activations