© 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. 41127
    Prev
    Next
    INDEX
    Explanations

    decibel values

    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
    erer
    -0.10
    enje
    -0.09
    APTER
    -0.09
    éĿ¢ç§¯è¾¾
    -0.09
    zung
    -0.09
    å¸ĮæľĽå¯¹æĤ¨
    -0.09
    иÑİ
    -0.09
    tene
    -0.09
    ä¸ĩ件
    -0.09
    ино
    -0.09
    POSITIVE LOGITS
    -
    0.06
    itics
    0.06
    ic
    0.06
    па
    0.06
    åİī害
    0.06
    åľı
    0.06
    ikov
    0.06
    ÙħØ©
    0.06
    ified
    0.06
    罩
    0.05
    Activations Density 0.002%

    No Known Activations