© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19733
    Prev
    Next
    INDEX
    Explanations

    continue reading

    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
    çĦ¶åIJİåıĪ
    -0.07
    ento
    -0.07
    .Export
    -0.06
    iedo
    -0.06
    abo
    -0.06
    yak
    -0.06
     sla
    -0.06
    "http
    -0.06
    upa
    -0.06
    ndo
    -0.05
    POSITIVE LOGITS
    æĤ£
    0.06
    æŀī
    0.06
    å¼Ĥ
    0.06
    æĸĩæĺİ
    0.06
    å±¥è¡Į
    0.06
    èĶ»
    0.06
    çijŀ
    0.05
    æĸĩåѦ
    0.05
    ìĪł
    0.05
    ä»ĩ
    0.05
    Activations Density 0.001%

    No Known Activations