© 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. 20103
    Prev
    Next
    INDEX
    Explanations

    genotype allele pairs

    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
    ä¹ĭçªĹ
    -0.09
    æijĨäºĨ
    -0.09
    ambo
    -0.08
    èİ«éĿŀ
    -0.08
    ussin
    -0.08
    cmds
    -0.08
    æĿ¥çļĦæŶåĢĻ
    -0.08
    广ä¹ī
    -0.08
     phá»ij
    -0.08
    ä¸įå¿į
    -0.08
    POSITIVE LOGITS
    æĪĸå°ij
    0.07
     or
    0.07
    راط
    0.06
    ycz
    0.06
    imonial
    0.06
    æĪĸæĺ¯
    0.06
    究
    0.06
    etos
    0.06
    xious
    0.06
    stras
    0.06
    Activations Density 0.004%

    No Known Activations