© 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. 43122
    Prev
    Next
    INDEX
    Explanations

    recurrence relations or sequences

    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
    æ²Ļæ²Ļ
    -0.08
    esm
    -0.07
    obo
    -0.07
    åѦåĮºæĪ¿
    -0.07
    æĭĸ
    -0.07
    åįĩåħ¥
    -0.07
    汽油
    -0.07
    atha
    -0.07
     gasoline
    -0.07
    åį³å¢¨
    -0.07
    POSITIVE LOGITS
     periodic
    0.09
    å¹´å¢ŀéķ¿
    0.08
     recurrence
    0.08
     growth
    0.07
     Cay
    0.07
    å¼ĢéĶģ
    0.07
    unchecked
    0.07
    ç³»
    0.07
    æķ°åĪĹ
    0.07
     unofficial
    0.07
    Activations Density 0.004%

    No Known Activations