© 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. 58043
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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
    æŀª
    -0.07
    ietet
    -0.07
    ศรี
    -0.06
    缸äºĴ
    -0.06
    ãĥ¡ãĥ³ãĥĪ
    -0.06
    oci
    -0.06
    ä½Ĩæĺ¯å¯¹äºİ
    -0.06
     Heck
    -0.06
    å¨ĵ
    -0.06
    æĥŁ
    -0.06
    POSITIVE LOGITS
    满å¿ĥ
    0.08
    andia
    0.08
    å¤ĩéĢī
    0.08
    OPTIONS
    0.07
    Options
    0.07
    åIJĦ项活åĬ¨
    0.07
    Æ°u
    0.07
    ;;;;
    0.07
    irage
    0.07
    åºĩ
    0.07
    Activations Density 0.002%

    No Known Activations