© 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. 56190
    Prev
    Next
    INDEX
    Explanations

    controversial subjects and disputes

    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
    stm
    -0.09
    ä»»ä½ł
    -0.09
    以赴
    -0.09
    spre
    -0.09
    ูล
    -0.09
    ðŁĺĢ
    -0.08
    çĴ¨
    -0.08
    akai
    -0.08
    IZATION
    -0.08
    arendra
    -0.08
    POSITIVE LOGITS
     whether
    0.13
    è¦ģä¸įè¦ģ
    0.13
    ä¸įåĨ³
    0.12
    whether
    0.11
    æĺ¯åIJ¦
    0.11
    æĺ¯åIJ¦éľĢè¦ģ
    0.11
     Whether
    0.10
     disputed
    0.10
    æĺ¯åIJ¦åľ¨
    0.10
    æĺ¯åIJ¦ä¸º
    0.10
    Activations Density 0.123%

    No Known Activations