© 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. 20625
    Prev
    Next
    INDEX
    Explanations

    Of course

    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
    ?):
    -0.06
    åħ·æľīçĭ¬ç«ĭ
    -0.06
    ÙģØ°
    -0.06
     سخ
    -0.06
    ä¼ļåĽłä¸º
    -0.06
    emberg
    -0.06
    ষà§įà¦ł
    -0.06
    ìķĺëĬĶëį°
    -0.06
    æĺİæĺİæĺ¯
    -0.06
    åıijå¸ĥåħ¬åijĬ称
    -0.06
    POSITIVE LOGITS
    sis
    0.06
    sd
    0.05
    tide
    0.05
    sein
    0.05
     pel
    0.05
     паÑģ
    0.05
     леÑĤ
    0.05
     ê°ľ
    0.05
    zd
    0.05
    fell
    0.05
    Activations Density 0.029%

    No Known Activations