© 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. 65162
    Prev
    Next
    INDEX
    Explanations

    get to experience

    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
    é¼ĵåĬ±åѦçĶŁ
    -0.07
    æ°Ķé¦ģ
    -0.07
    为äºĨç¡®ä¿Ŀ
    -0.07
    åĬĿ
    -0.07
     Auxiliary
    -0.07
    帮åĬ©çļĦ
    -0.06
    寻æ±Ĥ帮åĬ©
    -0.06
    Trust
    -0.06
    alsa
    -0.06
    è®°
    -0.06
    POSITIVE LOGITS
    梦å¯IJ以æ±Ĥ
    0.12
     freedom
    0.11
     enjoyment
    0.10
    èĩªçĶ±åº¦
    0.10
    çļĦä¹IJ趣
    0.10
     satisfying
    0.09
    ä¹ĭä¹IJ
    0.09
     freedoms
    0.09
    满足
    0.09
    çļĦçIJĨæĥ³
    0.09
    Activations Density 0.759%

    No Known Activations