© 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. 21352
    Prev
    Next
    INDEX
    Explanations

    sequence of actions

    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
    ç»ıè¿ĩäºĨ
    -0.08
    READING
    -0.07
     leo
    -0.07
    ç¾²
    -0.07
    oling
    -0.07
    onal
    -0.07
    æĺ¾ç¤ºäºĨ
    -0.07
    inken
    -0.07
    åı¯ä»¥è¢«
    -0.07
    rawn
    -0.07
    POSITIVE LOGITS
    åĬłä»¥
    0.09
     apply
    0.08
    æľīéĴĪ对æĢ§åľ°
    0.08
    ä¸įæĺ¯åIJĹ
    0.07
     use
    0.07
     deduct
    0.07
    称ä¹ĭ为
    0.07
     attribute
    0.07
    缸åºĶ
    0.07
    æĥ³åĬŀæ³ķ
    0.07
    Activations Density 0.318%

    No Known Activations