© 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. 58419
    Prev
    Next
    INDEX
    Explanations

    epic heroes and literature

    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
    ANGAN
    -0.08
    éŨåı£
    -0.07
    Parcel
    -0.07
    åīªåĪĢ
    -0.07
    abox
    -0.07
    emma
    -0.07
    ä¹īåĬ¡æķĻèĤ²éĺ¶æ®µ
    -0.06
     Solidar
    -0.06
    çĥ«ä¼¤
    -0.06
    è¡Ĺåı£
    -0.06
    POSITIVE LOGITS
    ì²Ļ
    0.08
    adj
    0.08
    axter
    0.07
    olim
    0.07
    人çĶŁ
    0.07
    æĪIJåĬŁåIJİ
    0.07
    amic
    0.07
    åįłåħ¨åĽ½
    0.07
    otá
    0.07
    åĴĮä»ĸçļĦ
    0.07
    Activations Density 0.003%

    No Known Activations