© 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. 19445
    Prev
    Next
    INDEX
    Explanations

    overlapping mathematical 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
    atora
    -0.08
    é£
    -0.08
    unden
    -0.08
    æī¹
    -0.07
    åĪĨåī²
    -0.07
    ä¸īäºĶ
    -0.07
    جÙĩ
    -0.07
    áŀ
    -0.07
    onton
    -0.07
    ZO
    -0.06
    POSITIVE LOGITS
    åıłåĬł
    0.09
     overlapping
    0.09
     overlap
    0.09
     overlaps
    0.08
    åĬłèµ·æĿ¥
    0.08
    _combined
    0.08
    æݥ踵
    0.08
    heet
    0.08
    æķĽ
    0.08
    æĭ¼æİ¥
    0.08
    Activations Density 0.044%

    No Known Activations