© 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. 47705
    Prev
    Next
    INDEX
    Explanations

    code comments and disclaimers

    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
    esson
    -0.09
     اÙĦأص
    -0.07
    åĬĪ
    -0.07
    å®Į
    -0.07
    ãģĭãģĦ
    -0.07
    ä¹ĸ
    -0.07
     hail
    -0.07
    rama
    -0.06
    pati
    -0.06
     stup
    -0.06
    POSITIVE LOGITS
    odic
    0.08
    积æŀģ主åĬ¨
    0.07
    pecially
    0.07
    åĨ°åĨ°
    0.07
    اÙħØ©
    0.06
    зок
    0.06
     плаÑĤе
    0.06
     Baca
    0.06
    Coords
    0.06
    ä¼Ļ
    0.06
    Activations Density 0.001%

    No Known Activations