© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64177
    Prev
    Next
    INDEX
    Explanations

    verbs and descriptions of operations

    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
    ä¸Ĭæĸ°
    -0.09
     
    -0.09
    utra
    -0.08
    åĴĮèµĦæºIJ
    -0.08
    æīĢåľ¨ä½įç½®
    -0.08
    ampp
    -0.08
    åĴĮä¸įèī¯
    -0.08
    noinspection
    -0.08
    æĬĬè¿Ļ个
    -0.08
    odb
    -0.08
    POSITIVE LOGITS
    èĢĮæĪIJ
    0.08
    并çĶ±
    0.08
    ÑģÑı
    0.07
    çļĦæĺ¯
    0.07
    ï¼Į
    0.07
    åħ¶ä¸Ń
    0.07
    å®Įæ¯ķ
    0.07
    æĪĸçĶ±
    0.06
    å®Įçķ¢
    0.06
    åħ¶
    0.06
    Activations Density 0.010%

    No Known Activations