© 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. 51017
    Prev
    Next
    INDEX
    Explanations

    converge or convergent

    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
    agher
    -0.09
    ation
    -0.08
    anvas
    -0.08
    ä¸ĢéĢļ
    -0.08
    enty
    -0.08
    eneration
    -0.08
    ä¸Ģæĭį
    -0.07
    agné
    -0.07
    kaar
    -0.07
    entication
    -0.07
    POSITIVE LOGITS
    er
    0.13
    ly
    0.09
    nya
    0.08
    erma
    0.08
    ting
    0.08
    Ùĩ
    0.08
    ebbe
    0.07
    uje
    0.07
    çļĦ
    0.07
    ges
    0.07
    Activations Density 0.001%

    No Known Activations