© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18607
    Prev
    Next
    INDEX
    Explanations

    concise request

    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
     pendek
    -0.08
    żeli
    -0.07
    amol
    -0.07
    leven
    -0.07
    åĬĽä½ľ
    -0.07
     espont
    -0.06
     Jés
    -0.06
    verket
    -0.06
    é«ĺä¸Ńéĺ¶æ®µ
    -0.06
    ÙħÙĬزات
    -0.06
    POSITIVE LOGITS
    -
    0.06
     thái
    0.05
     L
    0.05
     M
    0.05
    oire
    0.05
     ide
    0.05
    iny
    0.05
     squarely
    0.05
     E
    0.05
     (
    0.04
    Activations Density 0.003%

    No Known Activations