© 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. 38647
    Prev
    Next
    INDEX
    Explanations

    called, designation, diagnosis, trio, fourth

    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
    çĮ¿
    -0.07
    åŁİ乡
    -0.07
    ä¸īçݯ
    -0.06
    anova
    -0.06
    æĹłèī²
    -0.06
    tay
    -0.06
    ä¸Ĭä¼łåĽ¾çīĩ
    -0.06
    Įĵ
    -0.06
    _UNS
    -0.06
     fours
    -0.06
    POSITIVE LOGITS
    被称为
    0.10
    åı«åģļ
    0.10
    æīĢè°ĵçļĦ
    0.10
    称为
    0.10
     tzv
    0.10
    åij½åIJį为
    0.09
    ä¿Ĺ称
    0.09
     called
    0.09
    称ä¹ĭ为
    0.09
    稱çĤº
    0.09
    Activations Density 0.330%

    No Known Activations