© 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. 46958
    Prev
    Next
    INDEX
    Explanations

    corresponding to

    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
    æĻĥ
    -0.07
    åħ·
    -0.07
    voli
    -0.07
    spi
    -0.06
    å¤ļæł·
    -0.06
    央
    -0.06
     μÎŃ
    -0.06
    wier
    -0.06
    èĩ³
    -0.06
    VS
    -0.06
    POSITIVE LOGITS
     respectively
    0.29
     respective
    0.24
    åĪĨåĪ«æĺ¯
    0.23
    åĪĨåĪ«ä¸º
    0.23
    åĪĨåĪ«
    0.21
     ÑģооÑĤвеÑĤÑģÑĤвенно
    0.20
     respectiv
    0.19
    åĪĨåĪ¥
    0.19
    ãģĿãĤĮãģŀãĤĮ
    0.19
    åĪĨåĪ¥æĺ¯
    0.18
    Activations Density 0.119%

    No Known Activations