© 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. 17717
    Prev
    Next
    INDEX
    Explanations

    arbitrary manifolds

    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
    ItemAt
    -0.08
    amping
    -0.07
    ColumnName
    -0.07
    绿èī²çݯä¿Ŀ
    -0.07
    adesh
    -0.07
    addle
    -0.07
    æŀģ端
    -0.07
    _FLUSH
    -0.07
    utow
    -0.07
    riere
    -0.07
    POSITIVE LOGITS
    ä»»æĦı
    0.12
     arbitrary
    0.11
    éĿŀæłĩ
    0.10
     non
    0.09
    å¤įæĿĤçļĦ
    0.09
    éĿŀ
    0.09
    éļıæĦıçļĦ
    0.09
     complex
    0.08
    ä»»
    0.08
    ä¸įè§ĦåĪĻ
    0.08
    Activations Density 0.147%

    No Known Activations