© 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. 19212
    Prev
    Next
    INDEX
    Explanations

    material composition

    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
     continually
    -0.06
    òi
    -0.05
    é»ĺ认çļĦ
    -0.05
     perturb
    -0.05
    ãĥĬãĥ¼
    -0.05
    å¨ĺåŃIJ
    -0.05
    æ¶Ĥä¸Ĭ
    -0.05
    ä¸Ĭè¿Ľè¡Į
    -0.05
    é¢ľèī²åĴĮ
    -0.05
    outs
    -0.05
    POSITIVE LOGITS
    composition
    0.07
    ellet
    0.06
    filer
    0.06
    Composition
    0.06
    enan
    0.06
    æŀĦæĪIJ
    0.06
    æ§ĭæĪIJ
    0.06
    ags
    0.06
    æĮĩ示
    0.06
    容æĺĵ
    0.06
    Activations Density 0.011%

    No Known Activations