© 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. 12764
    Prev
    Next
    INDEX
    Explanations

    exist, equal, or divisible

    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
    ]*)
    -0.07
    pers
    -0.07
    agen
    -0.07
    **”
    -0.07
    æľīä»Ģä¹Ī
    -0.06
    ,DB
    -0.06
    ners
    -0.06
    ãģĹãģªãģĦãģ¨
    -0.06
     except
    -0.06
    åı®
    -0.06
    POSITIVE LOGITS
    ä»İèĢĮ使
    0.08
    itzt
    0.08
    èĩªå·±æĥ³è¦ģ
    0.08
    ä»İèĢĮ
    0.07
    ä¸ľå±±
    0.07
    åĵªæĢķæĺ¯
    0.07
    èĢĮè¿Ļ
    0.07
    foy
    0.07
     باÙĦض
    0.07
    ä»İèĢĮå½±åĵį
    0.07
    Activations Density 0.024%

    No Known Activations