© 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. 47262
    Prev
    Next
    INDEX
    Explanations

    fraction 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
    äºĮèĢħ
    -0.06
    ain
    -0.06
    adm
    -0.06
     thugs
    -0.06
    两èĢħ
    -0.06
    eter
    -0.06
     Giovan
    -0.06
    æŁIJ
    -0.06
    {}'.
    -0.06
    亦æľī
    -0.06
    POSITIVE LOGITS
    æĶ¶èĹıæľ¬ç«Ļ
    0.08
    ?,?,?,?,
    0.08
    ?,?,
    0.08
    åĩij
    0.07
    lund
    0.07
    æij¸äºĨ
    0.07
    kow
    0.07
    ulich
    0.07
    anford
    0.07
     Bolsa
    0.07
    Activations Density 0.008%

    No Known Activations