© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 33136
    Prev
    Next
    INDEX
    Explanations

    mathematical factorization patterns

    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
    æĸĹ
    -0.07
    çļĦéĿ¢åīį
    -0.07
    æ¥ĵ
    -0.07
    转æį¢æĪIJ
    -0.07
    è··
    -0.07
    षà¥įà¤Ł
    -0.07
    stride
    -0.07
    ersp
    -0.07
    ÑĤами
    -0.07
    ç»Ħç»ĩå¼Ģå±ķ
    -0.07
    POSITIVE LOGITS
    /single
    0.08
    åIJĪ并
    0.08
     merges
    0.07
     merging
    0.07
    merged
    0.07
    ä¼´éļı
    0.07
    åıªæľīä¸Ģ个
    0.07
    åļ
    0.07
    åĶ¯ä¸ĢçļĦ
    0.07
    sticky
    0.06
    Activations Density 0.004%

    No Known Activations