© 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. 46499
    Prev
    Next
    INDEX
    Explanations

    fractions and math notation

    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
    ,
    -0.06
    aldi
    -0.06
    ole
    -0.06
     elsewhere
    -0.06
     and
    -0.06
     splits
    -0.06
    �
    -0.05
    —
    -0.05
    ilia
    -0.05
     with
    -0.05
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.11
    è¡Įä¹ĭ
    0.09
    çĶŁæķĪä¹ĭæĹ¥èµ·
    0.09
    úc
    0.09
    ount
    0.08
    ses
    0.08
    æķ´ä¸ªäºº
    0.08
    **”
    0.08
    kses
    0.08
    大åĪ°
    0.08
    Activations Density 0.012%

    No Known Activations