© 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. 58262
    Prev
    Next
    INDEX
    Explanations

    package name followed by identifier

    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
    Ñģал
    -0.07
    qualified
    -0.07
    la
    -0.06
    hotel
    -0.06
    裡
    -0.06
    ahi
    -0.06
    éķ¿æķĪ
    -0.06
    lev
    -0.06
    iran
    -0.06
    uver
    -0.06
    POSITIVE LOGITS
    ä¸įèĥ½ä½ľä¸º
    0.08
    å¤ļä¸ªåĽ½å®¶
    0.08
    arrer
    0.07
    奥åĪ©
    0.07
    éºĹ
    0.07
    ãģĹãĤī
    0.07
     Chap
    0.07
    оÑģÑĤ
    0.07
    Ŀ
    0.07
    \Container
    0.07
    Activations Density 0.002%

    No Known Activations