© 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. 1341
    Prev
    Next
    INDEX
    Explanations

    supplementary services

    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
    ihan
    -0.08
    ÙĪرت
    -0.07
    plied
    -0.07
    urge
    -0.07
    /basic
    -0.07
    alik
    -0.07
    è²
    -0.07
    æļ¦
    -0.07
    主æĶ»
    -0.07
    ablish
    -0.07
    POSITIVE LOGITS
    éĶ¦ä¸Ĭæ·»èĬ±
    0.10
    è¡¥åħħ
    0.10
     additional
    0.09
     supplemental
    0.08
    é¢Ŀå¤ĸçļĦ
    0.08
     supplementary
    0.08
    é¢Ŀå¤ĸ
    0.08
     supplement
    0.08
    游离
    0.08
    ãĤĴ追åĬł
    0.08
    Activations Density 0.436%

    No Known Activations