© 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
    2. Qwen3.5-4B
    3. 15-RES-MATRYOSHKA-65K
    4. 17273
    Prev
    Next
    INDEX
    Explanations

    math and scientific notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    综åIJĪè¡ĮæĶ¿æī§æ³ķ
    -0.05
    _IGNORE
    -0.05
    اÙĦÙĬ
    -0.05
    é«ĺä½İ
    -0.05
     wre
    -0.05
    aign
    -0.05
    yi
    -0.05
    åħ¶ä»ĸæĸ¹å¼ı
    -0.05
     Prescription
    -0.05
    äºĨä¸Ģè·³
    -0.05
    POSITIVE LOGITS
       
    0.06
    iales
    0.06
    è¯ģå®ŀåħ¶
    0.06
    áĥ£áĥļ
    0.05
     shar
    0.05
    NL
    0.05
    çľģéģĵ
    0.05
    aurus
    0.05
    ial
    0.05
    ium
    0.05
    Activations Density 0.001%

    No Known Activations