© 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. 46873
    Prev
    Next
    INDEX
    Explanations

    report information

    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
    /her
    -0.09
    bourne
    -0.09
    tures
    -0.08
    arella
    -0.08
    ncmp
    -0.08
    entication
    -0.08
    esimo
    -0.08
    代表大ä¼ļ
    -0.08
    tics
    -0.08
    istrator
    -0.08
    POSITIVE LOGITS
    edly
    0.11
    Ñĩик
    0.07
    خاÙĨÙĩ
    0.07
    orial
    0.07
    äºĭ项
    0.07
    à¸ģารà¸ĵà¹Į
    0.07
    ä¸ĢåĪĻ
    0.07
     cáo
    0.06
    licate
    0.06
    acco
    0.06
    Activations Density 0.077%

    No Known Activations