© 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. 17271
    Prev
    Next
    INDEX
    Explanations

    saying mistake, soon to, last explanation

    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
    idot
    -0.07
    ynu
    -0.07
    antemente
    -0.07
    à¸Īà¹Į
    -0.06
    eens
    -0.06
    ä¹ĭéŃĤ
    -0.06
    oriously
    -0.06
     sÃŃmb
    -0.06
    возмо
    -0.06
    ÑĢоÑĤ
    -0.06
    POSITIVE LOGITS
    abstract
    0.05
    æĬ½è±¡
    0.05
     abstract
    0.05
    忽
    0.05
     quarter
    0.05
    ä¸ĸ
    0.05
    é¼İ
    0.05
     feder
    0.05
     Pitch
    0.04
     admir
    0.04
    Activations Density 0.002%

    No Known Activations