© 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. 60278
    Prev
    Next
    INDEX
    Explanations

    will + future action

    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
    ationally
    -0.08
    èĭ¥æĺ¯
    -0.07
    ä¼ļåIJĮ
    -0.07
    mtree
    -0.07
    尾页
    -0.07
    vision
    -0.07
    èĭ¥åľ¨
    -0.07
    ä¸ĩä¸Ģ
    -0.07
    زاÙĦ
    -0.07
    vinc
    -0.07
    POSITIVE LOGITS
    hent
    0.08
     gladly
    0.08
    ihn
    0.08
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    0.07
    hely
    0.07
    åĭĻ
    0.07
     bientôt
    0.07
    æĪijæĿ¥è¯´
    0.07
    çļĵ
    0.06
    åĻ¨çŃī
    0.06
    Activations Density 0.014%

    No Known Activations