© 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. 11470
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables

    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
    ç¨ĭ
    -0.07
    ç©·
    -0.06
     ade
    -0.06
     Yup
    -0.06
    iler
    -0.06
    项
    -0.06
    /
    -0.06
    reo
    -0.06
    ½
    -0.06
    ç¯Ļ
    -0.06
    POSITIVE LOGITS
    inser
    0.09
    armor
    0.08
    erber
    0.08
    hd
    0.08
    Ñĥма
    0.08
    éĩijèĬ±
    0.08
    rilla
    0.08
     ëijĺ룬
    0.07
    datatype
    0.07
    æĦļ人
    0.07
    Activations Density 0.006%

    No Known Activations