© 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. 20154
    Prev
    Next
    INDEX
    Explanations

    language proficiency and abilities

    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
    able
    -0.05
    r
    -0.05
    å®ŀæĸ½åĬŀæ³ķ
    -0.05
     bearing
    -0.05
     earnest
    -0.05
    åijĨ
    -0.04
    a
    -0.04
    -0.04
    丰å¯Įå¤ļ彩çļĦ
    -0.04
     lost
    -0.04
    POSITIVE LOGITS
    å²Ĺ
    0.07
    woke
    0.06
    clado
    0.06
    à¸Ľà¸¹à¸Ļ
    0.06
    åĪĪ
    0.06
    åľ°ä½į
    0.06
    alendar
    0.06
     —————————
    0.06
    çĶŁçĶŁ
    0.06
    çļĦ人äºĨ
    0.06
    Activations Density 0.001%

    No Known Activations