© 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. 30717
    Prev
    Next
    INDEX
    Explanations

    prime factors or decomposition

    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
    湧
    -0.08
    ÑĪок
    -0.07
    æ¶Į
    -0.07
    åķ¡
    -0.07
    otong
    -0.07
    accia
    -0.07
    .convert
    -0.06
    berman
    -0.06
    ifice
    -0.06
    ÏĥÏĦι
    -0.06
    POSITIVE LOGITS
    åĪĨ解
    0.08
     decomposition
    0.08
    åĮħåIJ«äºĨ
    0.08
     composed
    0.08
     Composition
    0.07
    inkel
    0.07
    Composition
    0.07
     composition
    0.07
     decom
    0.07
     Decom
    0.07
    Activations Density 0.022%

    No Known Activations