© 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. 2190
    Prev
    Next
    INDEX
    Explanations

    financial results

    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
    iana
    -0.07
    indra
    -0.07
    æ¿
    -0.07
    ãģĿãĤį
    -0.07
     Expires
    -0.07
    ãģªãģİ
    -0.07
    locator
    -0.06
    Ø·Ùħ
    -0.06
     spacing
    -0.06
    æĸ¥
    -0.06
    POSITIVE LOGITS
    åĩĢåĪ©æ¶¦
    0.09
    äºıæįŁ
    0.09
    åĩĢ
    0.09
    /net
    0.09
    çĽĪä½Ļ
    0.09
     profitability
    0.08
     net
    0.08
    æł¸ç®Ĺ
    0.08
    å·®é¢Ŀ
    0.08
    edException
    0.08
    Activations Density 0.030%

    No Known Activations