© 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. 31075
    Prev
    Next
    INDEX
    Explanations

    Iron Man

    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
    arca
    -0.07
    antee
    -0.07
    antum
    -0.07
    èµĦéĩij管çIJĨ
    -0.07
    inkin
    -0.07
    voke
    -0.06
     tang
    -0.06
    instanc
    -0.06
    ¯¯
    -0.06
    änen
    -0.06
    POSITIVE LOGITS
    åıĬåIJĦç§į
    0.08
     ë¹Ħ롯íķľ
    0.07
    éĩįéĩį
    0.07
    ä½ĵç³»åĴĮ
    0.07
    æĪij们å°Ĩä¼ļ
    0.07
    iddleware
    0.07
    åıĬ
    0.07
    åĬĽåĴĮ
    0.06
    -heavy
    0.06
    ãĤĴãģ¯ãģĺãĤģ
    0.06
    Activations Density 0.013%

    No Known Activations