© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22627
    Prev
    Next
    INDEX
    Explanations

    paste

    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
    Negative Logits
    telen
    -0.07
    åĮĻ
    -0.06
     peacefully
    -0.06
     observation
    -0.06
    ضÙī
    -0.06
    bourg
    -0.06
    SingleOrDefault
    -0.06
     duo
    -0.06
    éĢļè¿ĩè¿ĻäºĽ
    -0.06
    对该
    -0.05
    POSITIVE LOGITS
    oj
    0.05
    ung
    0.05
    çĹķ
    0.05
    ub
    0.05
    insa
    0.05
    åĢ¾è¯ī
    0.05
    ulk
    0.05
    orno
    0.05
    æĿ¥ä¹ĭ
    0.05
    رج
    0.05
    Activations Density 0.007%

    No Known Activations