© 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. 56180
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    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
    ìłķìĿĺ
    -0.08
    .loadData
    -0.08
    ModelIndex
    -0.08
    essions
    -0.08
    isiv
    -0.08
    ellate
    -0.08
    lare
    -0.08
    æĬŀ
    -0.08
    æĪijçļĦè¯Ŀ
    -0.08
    åħ¼æĢ»ç»ıçIJĨ
    -0.08
    POSITIVE LOGITS
    å·¥ä½ľè¿Ľè¡ĮäºĨ
    0.07
     reportedly
    0.06
    é«ĺ人
    0.06
    解åĨ³è¿Ļ个éĹ®é¢ĺ
    0.06
    人åijĺè¿Ľè¡Į
    0.06
    nown
    0.06
    å±ħçĦ¶
    0.06
    æĸ¹æ³ķè¿Ľè¡Į
    0.06
     P
    0.06
    çŁ¥æĥħ
    0.06
    Activations Density 0.005%

    No Known Activations