© 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. 22355
    Prev
    Next
    INDEX
    Explanations

    encourage

    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
    ึà¸ģ
    -0.06
    ee
    -0.06
    uary
    -0.06
    ï¸İ
    -0.06
    imum
    -0.06
    mi
    -0.05
    beau
    -0.05
    ence
    -0.05
    oe
    -0.05
    lah
    -0.05
    POSITIVE LOGITS
    ighb
    0.07
    ä¹ĭåĪĹ
    0.06
    grap
    0.06
     ÑģÑĩаÑģÑĤÑĮÑİ
    0.06
    apura
    0.06
    寡
    0.06
    iatric
    0.06
    itect
    0.05
    elim
    0.05
     اÙĦدÙĬÙħÙĤ
    0.05
    Activations Density 0.011%

    No Known Activations