© 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. 21343
    Prev
    Next
    INDEX
    Explanations

    left and right

    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
    aston
    -0.06
    vand
    -0.06
    ccio
    -0.05
    eppe
    -0.05
    ãģ¾ãĤīãģªãģĦ
    -0.05
    该åĮº
    -0.05
    Ø·ÙĨ
    -0.05
    ä»Ģä¹Īéĥ½
    -0.05
    ساÙĦ
    -0.05
    azel
    -0.05
    POSITIVE LOGITS
    åĴĮåIJİ
    0.07
    uis
    0.06
    åĴĮä¸Ń
    0.06
    åĪ°å¤´
    0.06
    repos
    0.06
    åĴĮé»ij
    0.06
    ÑĥмÑĭ
    0.06
    icator
    0.06
    åı£æ°´
    0.06
    ity
    0.05
    Activations Density 0.068%

    No Known Activations