© 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. 21284
    Prev
    Next
    INDEX
    Explanations

    asking "what do you mean"

    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
    æĥ°
    -0.07
    çĤľ
    -0.07
    vig
    -0.07
    ottes
    -0.07
    ำ
    -0.07
    ãĤ¥
    -0.06
    petto
    -0.06
    éĺľ
    -0.06
    usp
    -0.06
     mou
    -0.06
    POSITIVE LOGITS
    /values
    0.07
    orada
    0.07
    å°½æľī
    0.07
     /*#__
    0.06
     skimage
    0.06
    é£ŀåĪ°
    0.06
    oples
    0.06
    æĴ¥
    0.06
    èle
    0.06
    ousy
    0.06
    Activations Density 0.006%

    No Known Activations