© 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. 2340
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and equations

    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
    å¾Īéķ¿
    -0.06
     multiple
    -0.06
    ingly
    -0.06
    å¤ļä½į
    -0.06
    enter
    -0.06
     ÙĦÙIJ
    -0.06
    西éŨ
    -0.06
    å®°
    -0.06
    multiple
    -0.06
     several
    -0.06
    POSITIVE LOGITS
    bán
    0.07
    óf
    0.07
    conds
    0.07
    ÑģÑĤÑĥпа
    0.07
    onos
    0.07
    hofer
    0.07
     showc
    0.07
    à¸ĺิ
    0.07
    uros
    0.07
    bose
    0.07
    Activations Density 0.052%

    No Known Activations