© 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. 19214
    Prev
    Next
    INDEX
    Explanations

    function, quality, sleep, disabling

    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
    ron
    -0.06
    ç«ĭãģ¦
    -0.06
     rapid
    -0.05
    æ¶Į
    -0.05
     plurality
    -0.05
    iono
    -0.05
    ÑĥÑĤ
    -0.05
    欣
    -0.05
    ÃŃn
    -0.05
    çŀ¬éĹ´
    -0.05
    POSITIVE LOGITS
    å®ĥ以
    0.06
    imp
    0.06
     Vict
    0.06
    ÏĦοÏĢοι
    0.06
    å®ĥä¼ļ
    0.06
    为æŃ¢
    0.05
    è¶ĬæĿ¥è¶Ĭå¤ļçļĦ
    0.05
    দà§įধ
    0.05
     menj
    0.05
     }}"><
    0.05
    Activations Density 0.036%

    No Known Activations