© 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. 34328
    Prev
    Next
    INDEX
    Explanations

    meaning or information requested

    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
    ä¸įåħ¥
    -0.08
    寿
    -0.08
    ä¼ļåıĺå¾Ĺ
    -0.07
    à¹īาย
    -0.07
    æĪijæ°¸è¿ľ
    -0.07
    å§ĭ
    -0.07
    .cg
    -0.07
    èµ·ãģį
    -0.07
    สิ
    -0.06
    ä¸įè´Ł
    -0.06
    POSITIVE LOGITS
     Angabe
    0.09
    angaben
    0.08
     Angaben
    0.08
    çĶ¨æ³ķ
    0.07
     measured
    0.07
    æľīçļĦæĺ¯
    0.07
    /misc
    0.07
    ç»ıæŁ¥
    0.06
     údaj
    0.06
    æį¢ç®Ĺ
    0.06
    Activations Density 0.004%

    No Known Activations