© 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. 42042
    Prev
    Next
    INDEX
    Explanations

    entity identifier or category

    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
    ä¸ĢæľĿ
    -0.08
    anlı
    -0.08
    æª
    -0.08
    nja
    -0.08
    çļĦä¸ĢåĪĩéĥ½
    -0.08
    æĹ¥çĶŁ
    -0.08
    æĪijçļĦä¼ģä¸ļ
    -0.07
    ĥĿ
    -0.07
    lash
    -0.07
    mee
    -0.07
    POSITIVE LOGITS
     whose
    0.12
     tertentu
    0.09
     previously
    0.09
     previamente
    0.08
    whose
    0.08
    çī¹å®ļçļĦ
    0.08
     zuvor
    0.08
     cujo
    0.07
     cuyo
    0.07
    iori
    0.07
    Activations Density 0.389%

    No Known Activations