© 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. 49097
    Prev
    Next
    INDEX
    Explanations

    legal case status

    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
    åľı
    -0.08
    pty
    -0.07
    ç´Ĭä¹±
    -0.07
    -legged
    -0.07
    ÄĥtÄĥ
    -0.07
    ayload
    -0.06
    çļ¿
    -0.06
    ænd
    -0.06
    aptor
    -0.06
    ÙħÙĨ
    -0.06
    POSITIVE LOGITS
    erat
    0.09
    hafte
    0.09
    主çļĦ
    0.08
    审çIJĨ
    0.08
    ele
    0.08
    rchive
    0.08
    eki
    0.08
    дÑĢ
    0.08
    ee
    0.07
    edException
    0.07
    Activations Density 0.010%

    No Known Activations