© 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. 13098
    Prev
    Next
    INDEX
    Explanations

    extension and extend

    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
    æīĢæĮĩ
    -0.07
    天ä¸ĭ
    -0.07
    èı²çī¹
    -0.06
    èĩªå·±åĬ¨æīĭ
    -0.06
    nested
    -0.06
     nested
    -0.06
    å¤Ħäºİ
    -0.06
    ÑĢд
    -0.06
    æİĴæĶ¾
    -0.06
     rise
    -0.06
    POSITIVE LOGITS
    -extension
    0.09
    Å¡n
    0.09
    holt
    0.09
    ä¸įä¹ħçļĦ
    0.09
    ozn
    0.09
    æĪIJ大
    0.08
    æī©
    0.08
    à¸Ĥยาย
    0.08
    /ext
    0.08
    åĪ°æĸ°
    0.08
    Activations Density 0.010%

    No Known Activations