© 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. 20127
    Prev
    Next
    INDEX
    Explanations

    special characters and foreign words

    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
    ategor
    -0.06
    åĨłçĬ¶çĹħæ¯Ĵ
    -0.06
    è°ĥ
    -0.06
    æľ¯è¯Ń
    -0.05
    .ls
    -0.05
    abei
    -0.05
    valo
    -0.05
     prol
    -0.05
    ä¾ĥ
    -0.05
     ÙĪظ
    -0.05
    POSITIVE LOGITS
    çĦļ
    0.06
    olerance
    0.06
    æĶ¿
    0.06
    åħī大
    0.06
     unread
    0.05
    {
    0.05
    åıijçĶŁåľ¨
    0.05
     places
    0.05
     syn
    0.05
     burn
    0.05
    Activations Density 0.019%

    No Known Activations