© 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. 18693
    Prev
    Next
    INDEX
    Explanations

    condenser, condensation, condensed milk

    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
    ç§ī
    -0.08
    ÙĬتÙĬÙĨ
    -0.06
    presenta
    -0.06
    edom
    -0.06
    ongi
    -0.05
    è¦Ĩ
    -0.05
    loom
    -0.05
    ä¼°
    -0.05
    çİĦå¹»å°ı说
    -0.05
    ä¸įçŁ¥éģĵ
    -0.05
    POSITIVE LOGITS
    åĽŀæµģ
    0.06
    æ³£
    0.06
    æŃ¢è·Į
    0.06
    ingly
    0.06
     reverse
    0.05
     neg
    0.05
    æĻĸ
    0.05
    çªĴ
    0.05
    áles
    0.05
    ÑĩаÑģÑĤи
    0.05
    Activations Density 0.007%

    No Known Activations