© 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. 22616
    Prev
    Next
    INDEX
    Explanations

    less than

    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
    ale
    -0.06
    ä¹ĭ交
    -0.06
    ales
    -0.06
     premi
    -0.06
    ux
    -0.06
    aled
    -0.06
    esen
    -0.06
    embro
    -0.06
    ave
    -0.06
    potensi
    -0.06
    POSITIVE LOGITS
    amol
    0.07
    chaft
    0.06
    žno
    0.06
    çľĭ好çļĦ
    0.06
    falt
    0.06
    بت
    0.06
    nitt
    0.06
    rist
    0.06
    üter
    0.06
    encontre
    0.06
    Activations Density 0.013%

    No Known Activations