© 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. 8133
    Prev
    Next
    INDEX
    Explanations

    initials and acronyms from titles

    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
    ake
    -0.06
    +.
    -0.06
    å·²æĺ¯
    -0.06
    borough
    -0.05
     cou
    -0.05
    ÑģÑı
    -0.05
    eness
    -0.05
    è¾¹è§Ĵ
    -0.05
    åIJĮä¸Ģ个
    -0.05
    è¾¹
    -0.05
    POSITIVE LOGITS
     specifie
    0.08
    åī¯ç§ĺ书éķ¿
    0.08
    cito
    0.08
    è¡Įä¹ĭ
    0.08
    ByUsername
    0.08
     spokeswoman
    0.08
     melew
    0.08
    ./.
    0.08
    éĥ¨èIJ½æł¼
    0.08
    æ°´äºķ
    0.08
    Activations Density 0.001%

    No Known Activations