© 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. 20485
    Prev
    Next
    INDEX
    Explanations

    irritation of skin or eyes

    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
    ãĤ¿ãĥĥãĥĹ
    -0.06
     اÙĦÙĥت
    -0.06
     sunk
    -0.06
    æİĮæı¡äºĨ
    -0.06
    оба
    -0.06
     سÛĮا
    -0.06
    åĢ¼éĴ±
    -0.06
    åįłåįľ
    -0.06
    ÙĪÙĨد
    -0.06
     blackmail
    -0.05
    POSITIVE LOGITS
    ä¸įéĢĤåºĶ
    0.06
     sensitive
    0.06
    ensitive
    0.06
    æ¿Ģ
    0.05
    renal
    0.05
    aj
    0.05
    ä¸įç¦ģ
    0.05
    æķıæĦŁ
    0.05
    æĥ¹
    0.05
    Sensitive
    0.05
    Activations Density 0.016%

    No Known Activations