© 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. 26103
    Prev
    Next
    INDEX
    Explanations

    instructions on how to do something

    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
     ÑıкобÑĭ
    -0.09
    è¦ģèµ°
    -0.08
    ä½łåij¢
    -0.08
     supposedly
    -0.08
    æŁIJ
    -0.07
    æŁIJäºĽ
    -0.07
     dirinya
    -0.07
    å¤ļä¹Ī
    -0.07
    æŁIJ个
    -0.07
    æĪij们å¿ħé¡»
    -0.07
    POSITIVE LOGITS
     yourself
    0.17
     Yourself
    0.14
     yourselves
    0.12
    lah
    0.11
     your
    0.09
    ä¿ĿæĬ¤å¥½
    0.09
    ä½łçļĦæľĭåıĭ
    0.09
    кажиÑĤе
    0.09
    ä½łèĩªå·±çļĦ
    0.08
    åIJ§
    0.08
    Activations Density 0.131%

    No Known Activations