© 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. 43289
    Prev
    Next
    INDEX
    Explanations

    step length spacing

    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¸Ģè·¯
    -0.08
    ä½İåĬŁèĢĹ
    -0.08
    ä¿Ŀæľ¬
    -0.08
    utang
    -0.07
    師
    -0.07
    å¸ĪçļĦ
    -0.07
    itous
    -0.07
    亿åħĥ以ä¸Ĭ
    -0.07
    ä¸Ģè·¯ä¸Ĭ
    -0.07
    æ½¢
    -0.07
    POSITIVE LOGITS
    æŃ¥
    0.09
    uler
    0.08
    缩
    0.08
    uhn
    0.07
    bart
    0.07
    :auto
    0.07
    éĹ´éļĶ
    0.07
    交éĶĻ
    0.07
    Ticks
    0.07
    olph
    0.07
    Activations Density 0.004%

    No Known Activations