© 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. 26247
    Prev
    Next
    INDEX
    Explanations

    threshold

    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
    ×ĵ×ķת
    -0.08
    åģ¥åħ¨çļĦ
    -0.08
    xBB
    -0.08
    )=='
    -0.08
    xBE
    -0.08
    _FIXED
    -0.08
    ä¸ĭæĸĩ
    -0.08
    estina
    -0.08
    å°½åħ¶
    -0.08
    apak
    -0.08
    POSITIVE LOGITS
    ä»İèĢĮ
    0.07
    طار
    0.07
    اÙĤ
    0.06
    ä¸įè§ģ
    0.06
    æĢİä¹ĪåĬŀ
    0.06
     تÙĦÙĤ
    0.06
    ×Ļ×¢
    0.06
    ase
    0.06
    °
    0.06
    导èĩ´
    0.06
    Activations Density 0.012%

    No Known Activations