© 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. 15509
    Prev
    Next
    INDEX
    Explanations

    -old man

    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
    ä»ħä»£è¡¨ä½ľèĢħ
    -0.08
    orex
    -0.08
    tring
    -0.08
    arit
    -0.07
    angun
    -0.07
    łíĮ
    -0.07
    faq
    -0.07
    fa
    -0.07
    Fa
    -0.07
    æIJŀ
    -0.07
    POSITIVE LOGITS
    稽
    0.07
    uite
    0.07
    ç¯ĩäºĮ
    0.07
    elius
    0.07
    urop
    0.07
    าว
    0.06
    æīĢæĮģ
    0.06
    uration
    0.06
    æ±Ĥæĺ¯
    0.06
    رÙĪÙĬ
    0.06
    Activations Density 0.001%

    No Known Activations