© 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. 47868
    Prev
    Next
    INDEX
    Explanations

    Category: followed by a term

    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
    ahn
    -0.08
    jak
    -0.07
    æ¯Ķäºļ
    -0.07
     Leban
    -0.07
    aign
    -0.07
    .bn
    -0.07
    uby
    -0.07
    jo
    -0.07
    æĻ¶èݹ
    -0.07
    çĸ±
    -0.07
    POSITIVE LOGITS
    åijĬè¯īèĩªå·±
    0.08
    -console
    0.07
    .console
    0.07
    æ¯ĶåĪ«äºº
    0.07
    è¹Ń
    0.06
    tott
    0.06
     Brus
    0.06
    éļĪ
    0.06
    ÙĦÙģ
    0.06
    Poly
    0.06
    Activations Density 0.043%

    No Known Activations