© 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. 65509
    Prev
    Next
    INDEX
    Explanations

    falling or dropping

    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
    ðŁĺī
    -0.10
    enticate
    -0.10
    edig
    -0.09
    essant
    -0.09
    ALLY
    -0.09
    ãĥĥãĥĦ
    -0.09
     cadeau
    -0.09
    IALIZ
    -0.09
    ople
    -0.09
    inally
    -0.09
    POSITIVE LOGITS
    èIJ½çļĦ
    0.10
    ä¸ĭæĿ¥çļĦ
    0.10
     onto
    0.08
     into
    0.07
    èIJ½äºİ
    0.07
    æľīèĩ´
    0.06
    elling
    0.06
    æİīçļĦ
    0.06
    ä¸ĭæĿ¥
    0.06
    ä¸įä¸ĭæĿ¥
    0.06
    Activations Density 0.060%

    No Known Activations