© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39684
    Prev
    Next
    INDEX
    Explanations

    Conference proceedings and publications

    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
    è¿ĺæĺ¯ä»¥
    -0.07
    ossier
    -0.07
    zyb
    -0.07
    çĶŁæ´»æ°´å¹³
    -0.07
     courtesy
    -0.06
     recipro
    -0.06
    çļĦé«ĺä¸Ń
    -0.06
    ä¸ŃæĢ§
    -0.06
    orton
    -0.06
    zos
    -0.06
    POSITIVE LOGITS
    inqui
    0.08
    åĽ½ä¹ĭ
    0.07
    åįĥ人
    0.07
    æ¡£
    0.07
    ieme
    0.07
    alar
    0.07
    emachine
    0.07
    ordes
    0.07
    å¹´ä¼ļ
    0.07
    ÑıÑĤа
    0.07
    Activations Density 0.025%

    No Known Activations