© 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. 50348
    Prev
    Next
    INDEX
    Explanations

    example or question that

    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
     reta
    -0.07
    agung
    -0.07
    éľ
    -0.07
    ä¸į离
    -0.07
    ÑĢома
    -0.07
    omo
    -0.07
    ÐŁÐIJ
    -0.07
    translated
    -0.07
     поÑģи
    -0.06
    folios
    -0.06
    POSITIVE LOGITS
     infatti
    0.08
     specifically
    0.08
    çĶļèĩ³è¿ĺ
    0.07
    åħ·ä½ĵ
    0.07
    åħ·ä½ĵåĪĨæŀIJ
    0.07
    åħ·ä½ĵæĥħåĨµ
    0.07
     ugyanis
    0.07
    ä¹Łåı¯çĽ´æİ¥
    0.06
    çļĦåħ·ä½ĵæĥħåĨµ
    0.06
     totiž
    0.06
    Activations Density 0.015%

    No Known Activations