© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18710
    Prev
    Next
    INDEX
    Explanations

    such as

    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
    èī²åĪĹ
    -0.06
    ä¸ĢåĪ°
    -0.06
    ä¸ĢæŶ
    -0.06
    èIJ¥åķĨ
    -0.06
    osi
    -0.06
    egrad
    -0.05
    -sizing
    -0.05
    pute
    -0.05
    ä¸įæĺİçļĦ
    -0.05
    ee
    -0.05
    POSITIVE LOGITS
     softer
    0.06
    åľ°ä¹ħ
    0.06
    æt
    0.05
    çļĦå®ŀè·µ
    0.05
    çļĦæĸ¹åIJij
    0.05
    æħ
    0.05
    äºĨä¸ĢèĤ¡
    0.05
     оÑĢганизаÑĨиÑıми
    0.05
    æıIJä¾ĽæĶ¯æĮģ
    0.05
    gium
    0.05
    Activations Density 0.019%

    No Known Activations