© 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. 39447
    Prev
    Next
    INDEX
    Explanations

    math formula alignment

    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
    Ñıм
    -0.08
    åħħ
    -0.08
    Ĺı
    -0.07
    ury
    -0.07
    ãĤ¤ãĥ¬
    -0.07
    çıĤ
    -0.07
    ếm
    -0.07
     naqu
    -0.07
    以ä¸Ĭå°±æĺ¯
    -0.07
    æµģåħī
    -0.07
    POSITIVE LOGITS
    uchia
    0.06
    å¦Ĥæĺ¯
    0.06
    åŃ¦ä¹łåŀĭ
    0.06
    .instant
    0.06
     âĢŀ
    0.06
    quete
    0.06
    åıªæĺ¯ä¸ª
    0.06
    opter
    0.06
    ntag
    0.06
    åŁł
    0.06
    Activations Density 0.140%

    No Known Activations