© 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. 25454
    Prev
    Next
    INDEX
    Explanations

    mathematical sequences or progressions

    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
    intang
    -0.08
    íĺ¼
    -0.08
    äss
    -0.08
    owitz
    -0.08
    åľĺ
    -0.07
    åĽ¢
    -0.07
    AREN
    -0.07
    furter
    -0.07
    综åIJĪåĪĨæŀIJ
    -0.07
    AnimationFrame
    -0.07
    POSITIVE LOGITS
     middle
    0.08
    éļĶ
    0.08
    ä¸ŃéĹ´
    0.08
    middle
    0.07
     arithmetic
    0.07
     successive
    0.07
    åĬłåĢį
    0.07
     algebra
    0.07
    ä¸ŃéĹ´çļĦ
    0.07
     intermediate
    0.06
    Activations Density 0.003%

    No Known Activations