© 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. 20722
    Prev
    Next
    INDEX
    Explanations

    complementary, extend, alongside, or

    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
    -0.06
     nation
    -0.05
    次
    -0.05
    YP
    -0.05
    yl
    -0.05
    inating
    -0.05
     «
    -0.05
    迷离
    -0.05
     inherent
    -0.05
    åĪĴ
    -0.05
    POSITIVE LOGITS
     Rather
    0.07
    Rather
    0.07
    nton
    0.07
     sall
    0.06
     respectfully
    0.06
    èĢĮä¸įæĺ¯
    0.06
    pson
    0.06
    rather
    0.06
     presume
    0.06
    ttore
    0.06
    Activations Density 0.019%

    No Known Activations