© 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. 9855
    Prev
    Next
    INDEX
    Explanations

    numbers and repetitions

    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
    aza
    -0.08
    appen
    -0.07
    ename
    -0.07
    åıĮåıĮ
    -0.07
    FromBody
    -0.07
    çĥ¨
    -0.07
     vong
    -0.07
    çİ®
    -0.07
    führ
    -0.07
    æĺ¯ä¸Ģ对
    -0.07
    POSITIVE LOGITS
    رس
    0.07
     Concep
    0.07
    istrik
    0.07
    ç»´å¥ĩ
    0.07
    æĪĸéĥ¨åĪĨ
    0.07
    alai
    0.06
     misog
    0.06
    kozy
    0.06
    ลฯ
    0.06
    äºijå³°
    0.06
    Activations Density 0.022%

    No Known Activations