© 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. 20618
    Prev
    Next
    INDEX
    Explanations

    over time

    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
    边走
    -0.07
    åħ¶ä¸º
    -0.07
    äºİä¸ĸ
    -0.06
    space
    -0.06
    è¨Ģä¹ĭ
    -0.06
    å±Ģ
    -0.06
    (es
    -0.06
    sprech
    -0.06
    structuring
    -0.06
    ible
    -0.06
    POSITIVE LOGITS
    estos
    0.06
    è§ĦåĪĴåĴĮ
    0.06
    trup
    0.05
    leftright
    0.05
     pleinement
    0.05
    надÑĨаÑĤÑĮ
    0.05
    лÑıн
    0.05
    à¸Ĺัà¸Ļà¸Ĺี
    0.05
     неÑģко
    0.05
    æݧåĪ¶äºĨ
    0.05
    Activations Density 0.003%

    No Known Activations