© 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. 60510
    Prev
    Next
    INDEX
    Explanations

    Cameron, Putin, Syria

    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
    置身
    -0.08
    .freeze
    -0.07
     Sour
    -0.07
    åijĬ
    -0.06
    ç»Ħåijĺ
    -0.06
    飵
    -0.06
    IZER
    -0.06
    èĬ¸
    -0.06
    _super
    -0.06
    éĢļè¿ĩçĶµè¯Ŀ
    -0.06
    POSITIVE LOGITS
    ç»®
    0.08
    OrFail
    0.07
    äºijå³°
    0.07
    itia
    0.07
    én
    0.07
    éĻħ
    0.07
    ä¸įéĹ®
    0.07
    atable
    0.07
     dran
    0.07
    _dispatcher
    0.07
    Activations Density 0.005%

    No Known Activations