© 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. 22153
    Prev
    Next
    INDEX
    Explanations

    incomplete

    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
    ä¸įè¿ĩ
    -0.06
    ous
    -0.06
    lose
    -0.05
    orgetown
    -0.05
     neither
    -0.05
    ä»·åĢ¼åĴĮ
    -0.05
    æ¼Ĩ
    -0.05
    ubby
    -0.05
     commanding
    -0.05
    ÐłÐŀÐĴ
    -0.05
    POSITIVE LOGITS
     supp
    0.06
    маÑĤа
    0.06
    æľªå®Į
    0.06
     ë¶Ħëªħ
    0.06
    IMIT
    0.06
    æĹłæŃ¢
    0.06
    multipart
    0.06
     tramp
    0.06
    ä¸įçģŃ
    0.06
    Ø°ÙĬب
    0.05
    Activations Density 0.008%

    No Known Activations