© 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. 20302
    Prev
    Next
    INDEX
    Explanations

    I feel; I was; you raise

    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
    omie
    -0.06
    lÉĻ
    -0.06
    stel
    -0.06
    atro
    -0.06
    [âĢ¦
    -0.06
    ynd
    -0.06
    tel
    -0.05
    æıIJä¾Ľä¼ĺè´¨
    -0.05
     Ú©ÙĪت
    -0.05
    å¿ĥãĤĴ
    -0.05
    POSITIVE LOGITS
    çĽĪä½Ļ
    0.05
    ÙĬØ·
    0.05
    人
    0.05
    פ
    0.05
    ä»ĸ们è¿ĺ
    0.05
     عب
    0.05
    彿
    0.05
    æī©å±ķèµĦæĸĻ
    0.05
     exploit
    0.05
    linna
    0.05
    Activations Density 0.008%

    No Known Activations