© 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. 22119
    Prev
    Next
    INDEX
    Explanations

    case number or document number

    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
    åĴĮåıijå±ķ
    -0.08
    ä¹ĺé£İ
    -0.07
    ÙĪÙĦÙĬÙĨ
    -0.07
     finest
    -0.07
    éĺħè¯»æľ¬æĸĩåīį
    -0.07
    ä¸İåıijå±ķ
    -0.07
    åħ¨æľ¬å°ı说
    -0.07
    ä¸İåħ±
    -0.07
    ä»ĬçĶŁ
    -0.06
    iy
    -0.06
    POSITIVE LOGITS
    ournal
    0.08
    âĺĨ
    0.07
    åħ«å¤§
    0.07
    croft
    0.07
    atsu
    0.07
    LEMENT
    0.06
    astia
    0.06
    ä¹Ŀ大
    0.06
    áŁĦáŁĩ
    0.06
    ervo
    0.06
    Activations Density 0.003%

    No Known Activations