© 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. 3213
    Prev
    Next
    INDEX
    Explanations

    package and continuation

    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
    cess
    -0.08
    kken
    -0.07
    临走
    -0.07
    rolling
    -0.07
     <![
    -0.06
    åħ¶ä¸ŃåĮħæĭ¬
    -0.06
    æīĢæľīè¿ĻäºĽ
    -0.06
    Configurer
    -0.06
     Dol
    -0.06
    åĽ¾åºĵ
    -0.06
    POSITIVE LOGITS
    åĪĨ为
    0.09
    ancar
    0.09
    abor
    0.08
     bå
    0.08
    éĢIJ
    0.08
    åīį两
    0.08
    etter
    0.08
    åĪĴåĪĨ为
    0.08
    åĪĨå·¥
    0.07
    åĪĴåĪĨ
    0.07
    Activations Density 0.208%

    No Known Activations