© 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. 60708
    Prev
    Next
    INDEX
    Explanations

    sum and calculations

    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
    ibas
    -0.09
    Solo
    -0.08
    ibu
    -0.07
    ifix
    -0.07
    åĪ©çī©
    -0.07
    cide
    -0.07
    åij¨è¾¹çݯå¢ĥ
    -0.07
    jure
    -0.07
    ahu
    -0.07
    loyd
    -0.07
    POSITIVE LOGITS
     sum
    0.08
    sum
    0.08
    æĢ»éĩı
    0.08
    æĢ»æĶ¯
    0.08
    -sum
    0.08
    åIJĪ计
    0.08
    .sum
    0.08
    åħ¨èº«
    0.08
     summ
    0.08
     ìłĦì²´
    0.07
    Activations Density 0.018%

    No Known Activations