© 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. 31228
    Prev
    Next
    INDEX
    Explanations

    sources and elements

    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
    ixo
    -0.08
    यà¥ĭà¤Ĺ
    -0.08
    é«ĺæ¡¥
    -0.07
    byss
    -0.07
    éĻį
    -0.07
    èĴĤæĸ¯
    -0.07
    -Ta
    -0.07
    赫çĦ¶
    -0.07
    èĹı
    -0.07
    angka
    -0.07
    POSITIVE LOGITS
     propagation
    0.07
    ä¼ļ继ç»Ń
    0.07
    åIJİ继
    0.07
     Nearby
    0.07
     neighboring
    0.07
    åıijåĩºäºĨ
    0.07
     Huy
    0.07
    oris
    0.07
     forward
    0.07
     spreading
    0.07
    Activations Density 0.001%

    No Known Activations