© 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. 27770
    Prev
    Next
    INDEX
    Explanations

    numbers like 19xx

    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
    å¯
    -0.06
    Ùħ
    -0.06
    ·
    -0.06
    âĢ
    -0.06
    /
    -0.06
    rita
    -0.06
    ãĢĬ
    -0.06
    ÑħодиÑĤе
    -0.06
    ville
    -0.05
    رÙĬÙĤÙĬ
    -0.05
    POSITIVE LOGITS
    enje
    0.11
    anh
    0.11
    ernote
    0.09
    ë§ģ
    0.09
    ľ
    0.09
    ings
    0.09
    æľīæĿĥä¿ĿçķĻ
    0.09
    erate
    0.09
    isz
    0.09
    èī²åĪĹ
    0.09
    Activations Density 0.499%

    No Known Activations