© 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. 25836
    Prev
    Next
    INDEX
    Explanations

    before judges

    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
    æĶ¾è¿Ľåİ»
    -0.07
    ä¸ªé¡¹çĽ®
    -0.07
    æĻ
    -0.07
    ä¸Ģ个åŃĹ
    -0.07
    ฤษà¸İ
    -0.07
    ijken
    -0.07
    åĪĨéħįåĪ°
    -0.07
    %^
    -0.07
     graved
    -0.07
    è¿ĽåĪ°
    -0.07
    POSITIVE LOGITS
    arg
    0.07
    ZE
    0.07
    繫
    0.07
    ä½
    0.06
     proto
    0.06
    å¦ĥ
    0.06
    sstr
    0.06
    aning
    0.06
    container
    0.06
    cts
    0.06
    Activations Density 0.003%

    No Known Activations