© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39376
    Prev
    Next
    INDEX
    Explanations

    equipment processing

    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
     broken
    -0.07
    æĮīçħ§è§Ħå®ļ
    -0.07
     Broken
    -0.07
    ignant
    -0.06
    æ¶Ľ
    -0.06
    ider
    -0.06
    ocre
    -0.06
     fles
    -0.06
    elah
    -0.06
    broken
    -0.06
    POSITIVE LOGITS
    ersch
    0.07
    客
    0.07
    ween
    0.07
     اÙĦض
    0.07
    ï¿
    0.07
     Binh
    0.07
    dav
    0.06
    æīĺ
    0.06
     Buf
    0.06
    ingle
    0.06
    Activations Density 0.024%

    No Known Activations