© 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. 60919
    Prev
    Next
    INDEX
    Explanations

    historical context and writers

    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
    -bin
    -0.08
    åĵŃéĹ¹
    -0.08
    intang
    -0.08
    ppy
    -0.08
    åĩĨç¡®æĢ§åĴĮåIJĪæ³ķæĢ§
    -0.07
    /constants
    -0.07
    aldi
    -0.07
    çī¹å°Ķ
    -0.07
     بÙħÙĪجب
    -0.07
    ROL
    -0.07
    POSITIVE LOGITS
    å½ĵæŶçļĦ
    0.09
    å½ĵæŶ
    0.09
    çİ°å®ŀä¸Ń
    0.08
    çķ¶æĻĤ
    0.08
    çİ°å®ŀæĦıä¹ī
    0.07
    çī§
    0.07
    æ·±å±Ĥ
    0.07
     damal
    0.07
    å¤Ħå¢ĥ
    0.07
    åı¯ä»¥çIJĨ解
    0.07
    Activations Density 0.084%

    No Known Activations