© 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. 45613
    Prev
    Next
    INDEX
    Explanations

    sorting numbers and values

    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
    æĿIJ
    -0.07
    truk
    -0.07
    æĺİä¿¡
    -0.07
    olec
    -0.07
    noon
    -0.07
    alted
    -0.07
    leigh
    -0.07
    enders
    -0.07
    adj
    -0.07
    éļĪ
    -0.07
    POSITIVE LOGITS
     scramble
    0.07
     scrambled
    0.07
    ä¸Ģ鸣
    0.07
    StyleSheet
    0.07
     Sorting
    0.06
    Sorting
    0.06
     nad
    0.06
    æŀ¸
    0.06
     scram
    0.06
    ymo
    0.06
    Activations Density 0.036%

    No Known Activations