© 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. 56777
    Prev
    Next
    INDEX
    Explanations

    researchers discovering

    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
    åIJĪçIJĨå®īæİĴ
    -0.09
    !!!!
    -0.09
    /her
    -0.09
    !!!!!
    -0.08
    !!!!!!!!
    -0.08
     !!!!
    -0.08
    顺åĪ©çļĦ
    -0.08
    åĴĮè°IJåıijå±ķ
    -0.08
    æľī以ä¸ĭ
    -0.08
    /she
    -0.08
    POSITIVE LOGITS
    —and
    0.11
    —or
    0.11
     —
    0.11
     ÂŃ
    0.10
    —which
    0.09
    –and
    0.09
     --
    0.09
    —but
    0.09
    çľĭä¸Ĭåİ»
    0.09
    Âł
    0.08
    Activations Density 3.647%

    No Known Activations