© 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. 41967
    Prev
    Next
    INDEX
    Explanations

    visitors toyou insideyou guys

    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
    ulton
    -0.07
    å¿«èµ°
    -0.07
    зон
    -0.07
    æŃ¥åŃIJ
    -0.07
    æľīä½į
    -0.06
    nost
    -0.06
    éģŃåĪ°äºĨ
    -0.06
     Coast
    -0.06
    ä¸įå®ĮåĸĦ
    -0.06
    arest
    -0.06
    POSITIVE LOGITS
    å¤Ħ
    0.08
    ino
    0.08
    å¤ĦçļĦ
    0.08
    顺
    0.08
    æīĢåľ¨
    0.08
    æīĢåľ¨çļĦ
    0.07
    Ùİد
    0.07
    ä½įäºİ
    0.07
    berry
    0.07
    ç¶
    0.07
    Activations Density 0.001%

    No Known Activations