© 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. 46728
    Prev
    Next
    INDEX
    Explanations

    hopscotch, dosa, jiaozi, board, bars, falafel, cake, latkes

    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
    èĢģèĢģå®ŀ
    -0.06
    çĤĸ
    -0.06
    -dependent
    -0.06
    åģļèıľ
    -0.06
    æ³¢æ¾ľ
    -0.06
    æĹ¥çĶ¨
    -0.06
    åĪĢåĪĥ
    -0.06
    çŃīåĽłç´ł
    -0.06
     I
    -0.06
    ewing
    -0.06
    POSITIVE LOGITS
    æĺ¯ä¸Ģ项
    0.10
     PARTY
    0.09
    hão
    0.08
    lägg
    0.08
    举åįİ
    0.08
    çİ©æ³ķ
    0.08
    æĺ¯ä¸Ģç§į常è§ģçļĦ
    0.08
    çļĦä¹IJ趣
    0.08
    Ñħло
    0.08
    çİ©çİ©
    0.08
    Activations Density 0.179%

    No Known Activations