© 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. 17191
    Prev
    Next
    INDEX
    Explanations

    classification and categorization

    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
     tant
    -0.07
    æ·±åħ¥å®ŀæĸ½
    -0.07
    å¼ĤæĢ§
    -0.07
     swapped
    -0.06
    ANT
    -0.06
    naie
    -0.06
     ANT
    -0.06
     cá»ijt
    -0.06
    ØŃÙĨ
    -0.06
    æĹĭé£İ
    -0.06
    POSITIVE LOGITS
    åĪĨç±»
    0.15
     classifications
    0.14
     classification
    0.14
     categor
    0.14
    åĪĨ级
    0.14
    çļĦåĪĨç±»
    0.14
    è¿Ľè¡ĮåĪĨç±»
    0.14
     classify
    0.13
     categories
    0.13
     categorized
    0.13
    Activations Density 0.448%

    No Known Activations