© 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. 47035
    Prev
    Next
    INDEX
    Explanations

    without or beyond

    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
    ä¿ŀ
    -0.07
    缮
    -0.06
    rost
    -0.06
     totiž
    -0.06
    å¼ı设计
    -0.06
    æľīåħ³äºİ
    -0.06
    çĶµèĦijçīĪ
    -0.06
    /logging
    -0.06
    éĿŀ常çļĦ
    -0.06
    æľīåħ³ç³»
    -0.06
    POSITIVE LOGITS
     without
    0.09
    without
    0.08
    å¸ĥæĭī
    0.08
     Without
    0.08
     beyond
    0.08
    è¿ijåľ¨
    0.08
    ãģłãģijãģ§ãģªãģı
    0.08
     multiplier
    0.08
    iglio
    0.08
     WITHOUT
    0.08
    Activations Density 0.144%

    No Known Activations