© 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. 14916
    Prev
    Next
    INDEX
    Explanations

    chemical compound 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
    ä¸ĢåĪĻ
    -0.07
    hausen
    -0.07
    ë°Ķë¡ľ
    -0.07
    ä¸Ńæī¾åĪ°
    -0.06
    idor
    -0.06
    æīĢ以æĪij们
    -0.06
    Invoker
    -0.06
    èªī为
    -0.06
     least
    -0.06
     status
    -0.06
    POSITIVE LOGITS
    ä¸ĭåIJĮ
    0.12
    ãĥIJãĥ³ãĤ¯
    0.07
    att
    0.07
    aml
    0.07
    empi
    0.07
    igne
    0.06
    लà¤Ĺ
    0.06
    Compiled
    0.06
    onsor
    0.06
    vény
    0.06
    Activations Density 0.010%

    No Known Activations