© 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. 23098
    Prev
    Next
    INDEX
    Explanations

    verbed actions completed

    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
    ä»İä¸Ģ个
    -0.08
    å¾Īç´¯
    -0.08
    ature
    -0.07
    пин
    -0.07
    å¹´ç§ĭåŃ£
    -0.07
    uston
    -0.07
    saus
    -0.07
     kast
    -0.07
    umer
    -0.07
    artz
    -0.07
    POSITIVE LOGITS
    elles
    0.07
    onne
    0.06
    åļ
    0.06
    Âł
    0.06
    ipt
    0.06
    -dd
    0.06
    转åĮĸ
    0.06
     ’
    0.06
    bnb
    0.06
     ones
    0.06
    Activations Density 0.359%

    No Known Activations