© 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. 29605
    Prev
    Next
    INDEX
    Explanations

    letters A or Alpha

    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
    亡
    -0.07
    s
    -0.07
    ç´ĦæĿŁ
    -0.07
    vergence
    -0.06
    pon
    -0.06
     xmin
    -0.06
    à¹Ĥà¸Ļà¹īม
    -0.06
    otr
    -0.06
    å¼ķ诱
    -0.06
    otence
    -0.06
    POSITIVE LOGITS
    inga
    0.08
     domicili
    0.07
    éĺŁåĴĮ
    0.07
    etical
    0.07
    éļĬ
    0.07
    稽
    0.07
    abbrev
    0.06
     whose
    0.06
    çݲ
    0.06
    份
    0.06
    Activations Density 0.155%

    No Known Activations