© 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. 47548
    Prev
    Next
    INDEX
    Explanations

    until lifetime, deal, retaliation, heat loss, battle, exogenous

    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
    enstein
    -0.08
    epat
    -0.07
     jednos
    -0.07
    lyn
    -0.07
    ż
    -0.07
    ç²Ł
    -0.07
    æ·ĭ
    -0.06
     Avent
    -0.06
    иÑģпÑĥÑģка
    -0.06
    .azure
    -0.06
    POSITIVE LOGITS
    isel
    0.07
    çĽ¸ä¼ł
    0.07
    两家
    0.07
    isar
    0.07
    æľĢåIJİ
    0.06
    Ill
    0.06
    ÐĽÐŀ
    0.06
    finder
    0.06
    ouw
    0.06
    èħĨ
    0.06
    Activations Density 0.065%

    No Known Activations