© 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. 10809
    Prev
    Next
    INDEX
    Explanations

    and disease or function

    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
    并使çĶ¨
    -0.08
    วà¸ģ
    -0.08
    idar
    -0.07
    å±Ī
    -0.07
    elo
    -0.07
    åĴĮåĪ©çĶ¨
    -0.07
    以ä¿ĿæĮģ
    -0.07
    åĴĮéľĢæ±Ĥ
    -0.07
    ä»ĭçŁ³
    -0.06
     earm
    -0.06
    POSITIVE LOGITS
     ultimately
    0.09
    æĬµå¾¡
    0.08
    è¿ĽèĢĮ
    0.08
     ê¶ģ
    0.08
     ultimate
    0.07
    æľĢç»ĪçļĦ
    0.07
     overall
    0.07
     Ultimately
    0.07
    ä»ħæѤ
    0.07
     broader
    0.07
    Activations Density 0.427%

    No Known Activations