© 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. 10144
    Prev
    Next
    INDEX
    Explanations

    numbers, groups of three, four, or more

    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
    à§ĩà¦ķ
    -0.08
    ibun
    -0.07
    .ordinal
    -0.07
    æĿİè½»
    -0.07
    æľīæĿ¡
    -0.07
    etem
    -0.07
    rint
    -0.07
    ounds
    -0.07
    äºĶ级
    -0.07
    çī¹åĪ«æĺ¯å¯¹
    -0.07
    POSITIVE LOGITS
    æĮĩçļĦæĺ¯
    0.10
    æĮĩçļĦ
    0.10
    å°±æĺ¯æĮĩ
    0.09
    æĮĩ
    0.09
    ä¸Ģç»Ħ
    0.09
    ä¹ĭ称çļĦ
    0.09
    æ³ĽæĮĩ
    0.09
     à¹Ħà¸Ķà¹īà¹ģà¸ģà¹Ī
    0.08
    åĪĨåĪ«æĺ¯
    0.08
    æīĢæĮĩ
    0.08
    Activations Density 0.056%

    No Known Activations