© 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. 46460
    Prev
    Next
    INDEX
    Explanations

    reading raw data

    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
    é¡
    -0.06
    /ca
    -0.06
     sogenannten
    -0.06
    inan
    -0.06
     sogenannte
    -0.06
    resta
    -0.06
    å¾ĭå¸ĪäºĭåĬ¡æīĢ
    -0.06
    ocen
    -0.06
    opr
    -0.06
    åħ¬ç«ł
    -0.06
    POSITIVE LOGITS
     tadi
    0.08
    åĪ«è®©
    0.08
    åŁºå±Ĥåħļ建
    0.08
    áŀ»
    0.07
    èĥ½åģļ
    0.07
    ä¾Ŀè§Ħ
    0.07
    åıĬæľīåħ³
    0.07
    issance
    0.07
    æĽ´åĪ«è¯´
    0.07
    åĺ´è¾¹
    0.07
    Activations Density 0.001%

    No Known Activations