© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64106
    Prev
    Next
    INDEX
    Explanations

    referred to as

    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
     Nordest
    -0.07
    æľīè¶³å¤ŁçļĦ
    -0.07
    igten
    -0.07
    iscal
    -0.07
    æİ§ç³»ç»Ł
    -0.07
    uson
    -0.07
    inée
    -0.07
    åıĸäºĨ
    -0.07
    ÙĪرÙĪ
    -0.06
    .fromJson
    -0.06
    POSITIVE LOGITS
    称为
    0.11
    称ä¹ĭ为
    0.10
    åı«åģļ
    0.10
    à¹Ģรียà¸ģวà¹Īา
    0.09
    被称为
    0.09
    è¿ĻæŃ£æĺ¯
    0.09
    稱çĤº
    0.09
    è¿Ļå°±æĺ¯
    0.08
    ç§°ä½ľ
    0.08
     rient
    0.08
    Activations Density 0.030%

    No Known Activations