© 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. 61384
    Prev
    Next
    INDEX
    Explanations

    chunk size, count, days

    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
    atis
    -0.07
    ä¸Ģé¢Ĺ
    -0.06
    æĮ¤
    -0.06
    ص
    -0.06
    æĩ¦
    -0.06
    æľīä¸Ģé¢Ĺ
    -0.06
    å¼
    -0.06
    篡
    -0.06
     '%'
    -0.06
    ä¸Ń带
    -0.06
    POSITIVE LOGITS
    roman
    0.09
    anager
    0.08
    åħ³äºĨ
    0.08
    panse
    0.08
    OSS
    0.08
    elpers
    0.08
    licant
    0.08
    RAF
    0.08
     lév
    0.08
    ektor
    0.07
    Activations Density 0.007%

    No Known Activations