© 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. 64641
    Prev
    Next
    INDEX
    Explanations

    best followed by award category

    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
    Ñģев
    -0.07
    客æĪ·çļĦéľĢæ±Ĥ
    -0.06
    uum
    -0.06
    åĻ
    -0.06
    ancier
    -0.06
    ments
    -0.06
     lap
    -0.06
    çľŁä¼ª
    -0.06
    unded
    -0.06
    [,
    -0.06
    POSITIVE LOGITS
     excellence
    0.11
     nominations
    0.09
     nominees
    0.09
    çŃīå¤ļ项
    0.09
    åįķ项
    0.09
     nomination
    0.09
     Excellence
    0.09
     kateg
    0.09
     nominate
    0.09
     legjobb
    0.09
    Activations Density 0.354%

    No Known Activations