© 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. 64989
    Prev
    Next
    INDEX
    Explanations

    formatting time or date

    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
    äºĨåIJ§
    -0.07
    оÑģÑĥ
    -0.07
    ãģķãĤī
    -0.07
    reece
    -0.07
    inde
    -0.07
    anee
    -0.07
    SenderId
    -0.06
    alach
    -0.06
    åĴĮ好
    -0.06
    åį³çĶ¨
    -0.06
    POSITIVE LOGITS
    åı¦ä¸Ģæĸ¹
    0.07
    ories
    0.07
    emberg
    0.07
    åįļæĸĩ
    0.07
    èĩ³æĸ¼
    0.07
     PROGMEM
    0.06
    èĢĮ对äºİ
    0.06
    åľ¨å¾Ī大ç¨ĭ度ä¸Ĭ
    0.06
     =================================================
    0.06
    ä¸İä¹ĭ
    0.06
    Activations Density 0.005%

    No Known Activations