© 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. 10744
    Prev
    Next
    INDEX
    Explanations

    sentence correctness

    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
    ores
    -0.08
    ore
    -0.08
    æķħåIJį
    -0.07
    èĥĨåŃIJ
    -0.07
    ä¸įè¦ģéĶĻè¿ĩ
    -0.07
    رÙĤ
    -0.07
    ç´¢æĢ§
    -0.07
    ult
    -0.07
    iscal
    -0.07
    å¯ĨåĪĩéħįåIJĪ
    -0.07
    POSITIVE LOGITS
     gramm
    0.12
     Gramm
    0.10
    è¯Ńä¹ī
    0.09
    è¯Ńæ³ķ
    0.09
    åı¥åŃIJ
    0.08
     sentence
    0.08
    gram
    0.08
    Gram
    0.08
     grammar
    0.08
    åı¥
    0.08
    Activations Density 0.022%

    No Known Activations