© 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. 29042
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with fractions and exponents

    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
    ={({
    -0.07
    éŀŃ
    -0.07
    ryp
    -0.07
    èį£åħī
    -0.06
    ç¡ķæŀľ
    -0.06
    ä¹ħèĢĮ
    -0.06
     bored
    -0.06
    ske
    -0.06
     noop
    -0.06
    trom
    -0.06
    POSITIVE LOGITS
    å¼¥
    0.10
    åį±
    0.09
    å¡ĶçļĦ
    0.08
    å¡Ķ
    0.08
    严éĩį
    0.08
    åĵŃ声
    0.08
    严éĩįçļĦ
    0.08
    folger
    0.07
    æĥĬ人çļĦ
    0.07
     оÑģÑĤÑĢой
    0.07
    Activations Density 0.003%

    No Known Activations