© 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. 24000
    Prev
    Next
    INDEX
    Explanations

    second tab, first positive

    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
     eng
    -0.07
    anko
    -0.07
    apo
    -0.07
    Õ«ÖĢ
    -0.07
    aber
    -0.07
    ksom
    -0.06
    ÑĤÑĢ
    -0.06
    åħ¶èģĮ
    -0.06
     mẽ
    -0.06
    esen
    -0.06
    POSITIVE LOGITS
    ersh
    0.08
    é©°
    0.08
    æķĻèĤ²åѦçĶŁ
    0.07
    sus
    0.07
    avn
    0.07
    é£İå°ĺ
    0.07
    imis
    0.07
     รีส
    0.07
    为éĩįçĤ¹
    0.07
     alone
    0.06
    Activations Density 0.074%

    No Known Activations