© 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. 17330
    Prev
    Next
    INDEX
    Explanations

    ` , - ` sequence

    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
    åĪ¶
    -0.08
    ä¸ĢæĪ·
    -0.08
    EDI
    -0.07
    ouri
    -0.07
    åĨµ
    -0.07
    åĪ¶çļĦ
    -0.07
    大éĩıçļĦ
    -0.07
     Campo
    -0.07
    ppy
    -0.07
    kre
    -0.07
    POSITIVE LOGITS
    oman
    0.08
    encana
    0.07
    uning
    0.07
    lobals
    0.07
    äºĪåijĬ
    0.07
    mega
    0.06
    olit
    0.06
     KEEP
    0.06
    argar
    0.06
    unread
    0.06
    Activations Density 0.016%

    No Known Activations