© 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. 40731
    Prev
    Next
    INDEX
    Explanations

    output is JVM implementation

    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
     tarif
    -0.07
    寸
    -0.06
    åĪĨ项
    -0.06
    áng
    -0.06
    ConfigurationException
    -0.06
    Forever
    -0.06
    è¡
    -0.06
    lø
    -0.06
    å¿Ĺ
    -0.06
    æIJŃä¹ĺ
    -0.06
    POSITIVE LOGITS
    éļıæľº
    0.09
    ä¸į对称
    0.09
    azza
    0.09
    è¿ĩç¨ĭä¸Ń
    0.09
     randomly
    0.09
    è¿ĩç¨ĭ
    0.08
    åĢ¾åIJijäºİ
    0.08
     randomness
    0.08
     asymmetric
    0.08
    éģİç¨ĭä¸Ń
    0.08
    Activations Density 0.069%

    No Known Activations