© 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. 46879
    Prev
    Next
    INDEX
    Explanations

    numbers or symbols in math problems

    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
    俨
    -0.07
    å¹
    -0.07
    agna
    -0.06
    ä½Ĩè¿Ļ
    -0.06
    este
    -0.06
    汪汪
    -0.06
     Plat
    -0.06
    ä¸į欲
    -0.06
    çĥ
    -0.06
     aff
    -0.06
    POSITIVE LOGITS
    оби
    0.07
    åľ¨äºĨ
    0.07
    çĭ¬
    0.07
    åķ¡
    0.07
    åı©
    0.07
    å¦ĤæѤä¹ĭ
    0.07
    list
    0.07
    aways
    0.06
    ator
    0.06
    olding
    0.06
    Activations Density 0.104%

    No Known Activations