© 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. 12035
    Prev
    Next
    INDEX
    Explanations

    markdown, Source, Forward

    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
    atico
    -0.07
    èŀºçº¹
    -0.07
    atz
    -0.06
    reements
    -0.06
    åļ·
    -0.06
     ranged
    -0.06
    essel
    -0.06
    -0.06
     маÑģÑģа
    -0.06
    缸æī£
    -0.06
    POSITIVE LOGITS
    elang
    0.08
    纶
    0.07
     `%
    0.07
     `$
    0.07
    nus
    0.07
    оди
    0.07
    ä¸İæľįåĬ¡
    0.07
    RAW
    0.07
    å¼ĢèĢĥ
    0.06
    nica
    0.06
    Activations Density 0.017%

    No Known Activations