© 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. 31396
    Prev
    Next
    INDEX
    Explanations

    units digit

    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
    èĢĮåľ¨äºİ
    -0.07
     clearfix
    -0.07
    abay
    -0.06
    åıªæľīè¿Ļæł·
    -0.06
    ony
    -0.06
    å°Ĩæľī
    -0.06
    åĪ°æŶåĢĻ
    -0.06
    çŃīæĸ¹å¼ı
    -0.06
    INTERNAL
    -0.06
     scope
    -0.06
    POSITIVE LOGITS
    AFX
    0.07
     selengkapnya
    0.07
    ÙģÙĤ
    0.07
    Narrated
    0.07
     Ùģرا
    0.07
    伦å¤ļ
    0.07
    åİļåİļçļĦ
    0.07
    roe
    0.07
    gré
    0.07
    ÃŃv
    0.07
    Activations Density 0.009%

    No Known Activations