© 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. 24837
    Prev
    Next
    INDEX
    Explanations

    prime factors

    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
    rase
    -0.07
     Rubin
    -0.07
    ç«ŀ
    -0.07
    -
    -0.06
    affe
    -0.06
     corresponding
    -0.06
    affer
    -0.06
    antis
    -0.06
    æĿ°
    -0.06
    otis
    -0.06
    POSITIVE LOGITS
    åĪĨ解
    0.13
    æĭĨ解
    0.11
     decomposition
    0.11
    æĭĨ
    0.11
    æĭĨåĪĨ
    0.10
    æĭĨå¼Ģ
    0.10
     decom
    0.10
     breakdown
    0.09
    åĽłæķ°
    0.09
     Decom
    0.09
    Activations Density 0.023%

    No Known Activations