© 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. 11587
    Prev
    Next
    INDEX
    Explanations

    spatial resolution and granularity

    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
    NotFoundError
    -0.09
    edException
    -0.09
    ments
    -0.08
    lesh
    -0.08
    æ´»åĬ¨ä¸Ńå¿ĥ
    -0.08
    ató
    -0.08
    ãĤĴãĤ¹ãĥĪãĥĥãĤ¯
    -0.08
    triz
    -0.08
    cier
    -0.08
    ÃŃv
    -0.08
    POSITIVE LOGITS
     finer
    0.10
    çŃī级çļĦ
    0.10
    çŃī级
    0.09
    çŃīç´ļ
    0.08
    级åĪ«
    0.07
    åĪĨ辨
    0.07
     finest
    0.07
    /detail
    0.07
    åı¯è¨Ģ
    0.07
     granularity
    0.07
    Activations Density 0.043%

    No Known Activations