© 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. 25545
    Prev
    Next
    INDEX
    Explanations

    examples from other languages

    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
    ç¡ķ士åѦä½į论æĸĩ
    -0.06
    åĴĮé¼ĵåĬ±
    -0.06
     distinguished
    -0.06
    ä½ľä¸ºä¸Ģç§į
    -0.06
    æ¯Ĥ
    -0.06
    -org
    -0.06
    -ins
    -0.06
    èĩªå·±å¯¹
    -0.06
     ins
    -0.06
    .inc
    -0.06
    POSITIVE LOGITS
    ä¾ĭå¦Ĥ
    0.12
     bijvoorbeeld
    0.11
    å¦Ĥçģ«
    0.09
    напÑĢимеÑĢ
    0.09
     напÑĢимеÑĢ
    0.09
     beispielsweise
    0.09
     például
    0.09
    æ¯Ķå¦Ĥ
    0.09
     misalnya
    0.08
     beispiels
    0.08
    Activations Density 0.421%

    No Known Activations