© 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. 45874
    Prev
    Next
    INDEX
    Explanations

    Jordan set, DCFL, measure theory, fractional Brownian motion

    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
    ä½Ļåħī
    -0.08
    è¦ļ
    -0.08
    ç¬Ļ
    -0.08
    èĮ¯èĭĵ
    -0.07
    Ứ
    -0.07
    转载请注æĺİåĩºå¤Ħ
    -0.07
    èĶļ
    -0.07
    amal
    -0.07
     Raya
    -0.07
    ingen
    -0.07
    POSITIVE LOGITS
    åĪĨ段
    0.10
    累积
    0.09
    segment
    0.09
    smooth
    0.08
    accum
    0.08
     segment
    0.08
     smooth
    0.08
     impulses
    0.08
    累计
    0.08
    è¿ŀç»ŃçļĦ
    0.08
    Activations Density 0.006%

    No Known Activations