© 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. 20164
    Prev
    Next
    INDEX
    Explanations

    action, function, file, present

    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
    [".
    -0.07
    说ä¸į
    -0.06
    ãĥĥãĤ±
    -0.06
    jer
    -0.06
    ff
    -0.06
    çĽĸ
    -0.06
    ule
    -0.06
    åĩ¶
    -0.06
    ("."
    -0.06
    fer
    -0.06
    POSITIVE LOGITS
    æĹłçŁ¥
    0.07
    Scaled
    0.07
    -opacity
    0.07
    nette
    0.07
    lickr
    0.07
    讲çļĦæĺ¯
    0.07
    stamp
    0.07
     pyt
    0.07
     zwar
    0.06
    edback
    0.06
    Activations Density 0.004%

    No Known Activations