© 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. 46869
    Prev
    Next
    INDEX
    Explanations

    primary

    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
    idia
    -0.07
    å¼¹
    -0.07
    teros
    -0.06
    ÑĤам
    -0.06
    æŁIJ
    -0.06
    ently
    -0.06
    æŁIJç§į
    -0.06
    ipun
    -0.06
    綿
    -0.06
    以ä¸Ģ个
    -0.06
    POSITIVE LOGITS
    主è¦ģæľī
    0.09
    æľīåĵªäºĽåij¢
    0.09
    éĥ½æľīåĵªäºĽ
    0.09
    æľīåĵªäºĽ
    0.09
    åıªæľī
    0.08
    èµ°éģį
    0.08
    èĮĥåĽ´ä¸º
    0.08
    寻æī¾
    0.08
    åĩ¡æĺ¯
    0.08
    æŁ¥çľĭæīĢæľī
    0.08
    Activations Density 0.005%

    No Known Activations