© 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. 13894
    Prev
    Next
    INDEX
    Explanations

    noun endings

    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
    žÃŃ
    -0.09
    หà¹Į
    -0.09
    importe
    -0.09
    èĢĮéĢĻ
    -0.08
    azes
    -0.08
    inally
    -0.08
    ève
    -0.08
    INAS
    -0.08
    Ø°Ùİا
    -0.08
    ÑĮÑĪе
    -0.08
    POSITIVE LOGITS
    ings
    0.12
    ation
    0.10
    ance
    0.09
    ness
    0.09
    à¸ģารà¸ĵà¹Į
    0.09
    ations
    0.09
    ments
    0.09
    æĢ§
    0.08
    ing
    0.08
    ÙĬØ©
    0.08
    Activations Density 0.286%

    No Known Activations