© 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. 32067
    Prev
    Next
    INDEX
    Explanations

    \n-- Abstract --

    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
    ç¼ĸè¾ijäºİ
    -0.09
    ĮĢ
    -0.09
    ä½łåį´
    -0.08
    æī©å±ķèµĦæĸĻ
    -0.08
    æľĢæĸ°æĸĩç«ł
    -0.08
    धà¥Ģ
    -0.08
    Interval
    -0.07
    éĤ£ä»½
    -0.07
    udas
    -0.07
    aniel
    -0.07
    POSITIVE LOGITS
    殿
    0.07
    ä¼ĹæīĢåij¨çŁ¥
    0.07
    涵
    0.06
    è¶ĭåĬ¿
    0.06
    è¯ļ
    0.06
    欣
    0.06
    çĦī
    0.06
    <p
    0.06
    rh
    0.06
    _From
    0.06
    Activations Density 1.185%

    No Known Activations