© 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. 21350
    Prev
    Next
    INDEX
    Explanations

    natural sources

    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
    çŀ¬æģ¯
    -0.09
    è¼Ķ
    -0.07
    åħħè¡Ģ
    -0.07
    åħ³éĹŃçªĹåı£
    -0.07
     fullest
    -0.07
    å½ķçĶ¨
    -0.07
     fuller
    -0.07
     dibentuk
    -0.07
    ture
    -0.07
     retract
    -0.07
    POSITIVE LOGITS
    Sources
    0.09
    éķ¿æľŁ
    0.09
     Rare
    0.09
     rare
    0.08
     sources
    0.08
    常年
    0.08
     zdro
    0.08
     yearly
    0.08
    éķ¿æľŁçļĦ
    0.08
    sources
    0.07
    Activations Density 0.024%

    No Known Activations