© 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. 28504
    Prev
    Next
    INDEX
    Explanations

    code structures

    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
    omid
    -0.08
    ones
    -0.07
    utam
    -0.07
    è¡·å¿ĥçļĦ
    -0.07
    zug
    -0.06
     Prado
    -0.06
    ÙĬÙĪÙĨ
    -0.06
    wards
    -0.06
    ay
    -0.06
    =__
    -0.06
    POSITIVE LOGITS
    åĭĩå¾Ģ缴åīį
    0.09
    俱ä¹IJéĥ¨
    0.08
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    0.08
    åĬłæĭ¿å¤§
    0.07
    ande
    0.07
    æ´ŀéĩĮ
    0.07
    arik
    0.07
     Adel
    0.06
    ousel
    0.06
    िà¤ķा
    0.06
    Activations Density 0.028%

    No Known Activations