© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26764
    Prev
    Next
    INDEX
    Explanations

    begin, end, foreign, key, President

    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
    pez
    -0.08
    dez
    -0.08
     mob
    -0.08
    ugd
    -0.07
    etter
    -0.07
    æł¼æł¼
    -0.07
     Ill
    -0.06
     gan
    -0.06
    éľĢè¦ģç»ıè¿ĩ
    -0.06
    ftime
    -0.06
    POSITIVE LOGITS
     tadi
    0.08
    çļĦåŁºç¡Ģä¸Ĭ
    0.08
    éħĭ
    0.06
    å¤Ł
    0.06
    ä¸Ĭè¿°
    0.06
    inz
    0.06
     канд
    0.06
    FY
    0.06
    éri
    0.06
    edList
    0.06
    Activations Density 0.149%

    No Known Activations