© 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. 44934
    Prev
    Next
    INDEX
    Explanations

    certain words or phrases

    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
    çļĦä¸Ģç§įæĸ¹å¼ı
    -0.10
    ä»»ä½ķåħ¶ä»ĸ
    -0.10
    ä»»ä½ķ
    -0.10
     any
    -0.09
    çŃīä¸Ģç³»åĪĹ
    -0.09
    çļĦéĤ£ä¸ĢåĪ»
    -0.08
    çļĦä¸ĢåĪĩéĥ½
    -0.08
    æľīä»»ä½ķ
    -0.08
    çļĦä¸ĢåĪĩ
    -0.08
    ä»»ä½ķè´¹çĶ¨
    -0.08
    POSITIVE LOGITS
    æ¯Ķå¦Ĥ
    0.10
     depending
    0.10
    æ¯Ķå¦Ĥåľ¨
    0.09
    depending
    0.09
    æ¯Ķå¦Ĥ说
    0.08
     durchaus
    0.08
    ä¾ĭå¦Ĥ
    0.08
    诸å¦Ĥ
    0.08
    Depending
    0.08
     dependiendo
    0.08
    Activations Density 0.500%

    No Known Activations