© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17588
    Prev
    Next
    INDEX
    Explanations

    adjective before noun

    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
     Damn
    -0.07
     darn
    -0.06
    cep
    -0.06
    Damn
    -0.06
    éĩľ
    -0.06
    Ñģловно
    -0.06
    äºĨä¸Ģå±Ĥ
    -0.05
    åģļ好äºĨ
    -0.05
     thÄĥng
    -0.05
    çİ°åľ¨å¼Ģå§ĭ
    -0.05
    POSITIVE LOGITS
     prest
    0.06
    lässlich
    0.06
    eneg
    0.05
    ä¸ĭæĮ«
    0.05
    elop
    0.05
    æ´²
    0.05
    大åħ³
    0.05
    åı£çļĦ
    0.05
    kuš
    0.05
    hung
    0.05
    Activations Density 0.185%

    No Known Activations