© 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. 32040
    Prev
    Next
    INDEX
    Explanations

    adjective

    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
    为载ä½ĵ
    -0.09
    _blocking
    -0.09
    igny
    -0.08
    åŁºæľ¬åİŁçIJĨ
    -0.08
    Logs
    -0.08
    λιά
    -0.08
    åħ´è¶£
    -0.08
    nTo
    -0.08
    _LOGGER
    -0.08
    irsch
    -0.08
    POSITIVE LOGITS
    ness
    0.12
    形容
    0.10
     adjective
    0.09
    形容è¯į
    0.08
     بÙĪدÙĨ
    0.08
    修饰
    0.08
    åıįä¹īè¯į
    0.08
    æĿ¥å½¢å®¹
    0.08
     ones
    0.08
    NESS
    0.08
    Activations Density 0.195%

    No Known Activations