© 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. 1965
    Prev
    Next
    INDEX
    Explanations

    if $

    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
    Å«d
    -0.07
     uintptr
    -0.07
    gia
    -0.06
    ingan
    -0.06
    ãģ¡ãĤĩãģĨ
    -0.06
    urin
    -0.06
    amet
    -0.06
    绣çŃ¹
    -0.06
    ioc
    -0.06
    jis
    -0.06
    POSITIVE LOGITS
    以ä¸ĭæĿ¡ä»¶
    0.09
    odob
    0.08
    wärts
    0.07
    çĴIJ
    0.07
    æ³¢ç½Ĺ
    0.07
    ÙĥÙĬ
    0.07
    éĢıäºĨ
    0.07
    å¦Ĥæĺ¯
    0.07
    æŁIJ天
    0.07
    ÑĢиÑģÑĤа
    0.07
    Activations Density 0.044%

    No Known Activations