© 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. 51280
    Prev
    Next
    INDEX
    Explanations

    return or restart

    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¸Ģè¾ĪåŃIJ
    -0.07
    çļĦå¿ĥå¾Ĺ
    -0.07
    æį¢ç®Ĺ
    -0.07
    æĹ©çĨŁ
    -0.07
    ianos
    -0.06
    人æŃ»äº¡
    -0.06
    ä¸ĢçĶŁ
    -0.06
    _convert
    -0.06
    _translate
    -0.06
    æ°¸
    -0.06
    POSITIVE LOGITS
    æģ¢å¤į
    0.24
    æģ¢å¤įäºĨ
    0.22
     restored
    0.22
    æģ¢å¤įåĪ°
    0.21
     restoration
    0.20
    æģ¢å¾©
    0.19
     restore
    0.19
     reinst
    0.19
     restoring
    0.19
    éĩįæĭ¾
    0.19
    Activations Density 0.534%

    No Known Activations