© 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. 17417
    Prev
    Next
    INDEX
    Explanations

    run and succeeding commands

    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
    ž
    -0.05
    à¸į
    -0.05
    ãģ©
    -0.05
    llu
    -0.05
    主æĮģä¼ļè®®
    -0.05
    mk
    -0.05
     lá»Ļ
    -0.05
    æ®Ĭ
    -0.05
    .mk
    -0.05
    ä½ķåħ¶
    -0.05
    POSITIVE LOGITS
    asses
    0.06
    odne
    0.06
    rani
    0.06
    -ending
    0.05
    озна
    0.05
     everytime
    0.05
    irie
    0.05
     insure
    0.05
    Bonus
    0.05
     Gabinete
    0.05
    Activations Density 0.007%

    No Known Activations