© 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. 23556
    Prev
    Next
    INDEX
    Explanations

    period followed by 2

    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
     Kansas
    -0.10
    Kansas
    -0.10
    rzy
    -0.09
    ç³ĸå°¿
    -0.09
    æľĿéĺ³åĮº
    -0.09
     UMK
    -0.08
    eph
    -0.08
    举åŁİåĮº
    -0.08
     Nairobi
    -0.08
     portug
    -0.08
    POSITIVE LOGITS
     Azerbai
    0.10
     Azerbaijan
    0.10
     Bahrain
    0.10
    èĭıå·ŀå¸Ĥ
    0.09
    æī¬å·ŀ
    0.09
    æ±Łèĭıçľģ
    0.09
    èĭıå·ŀ
    0.09
     Venezuelan
    0.08
     Eston
    0.08
    æ±Łå®ģ
    0.08
    Activations Density 0.957%

    No Known Activations