© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16798
    Prev
    Next
    INDEX
    Explanations

    URLs, names, code snippets

    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
    Negative Logits
    ipt
    -0.05
     navigator
    -0.05
     hydr
    -0.05
    enis
    -0.05
    oda
    -0.05
    è®ĬåĮĸ
    -0.05
    empl
    -0.05
    rome
    -0.05
    undu
    -0.05
     (!((
    -0.05
    POSITIVE LOGITS
    zum
    0.06
    åĨĮ
    0.06
    ommage
    0.06
    ÅĤek
    0.06
    ijn
    0.06
    ÐłÐĿ
    0.05
    ocos
    0.05
    >>,
    0.05
    æİĴ
    0.05
    æŁIJ
    0.05
    Activations Density 0.001%

    No Known Activations