© 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. 16712
    Prev
    Next
    INDEX
    Explanations

    names with possessives or relationships

    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
    å²ģçĶŁæĹ¥
    -0.06
     result
    -0.05
    樽
    -0.05
    é³
    -0.05
     SUN
    -0.05
     unw
    -0.05
    result
    -0.05
     aqu
    -0.05
    config
    -0.05
     qualities
    -0.05
    POSITIVE LOGITS
    itom
    0.08
    iché
    0.07
     اÙĦعزÙĬز
    0.07
    taa
    0.06
    garten
    0.06
    tait
    0.06
    té
    0.06
    ÑĢÑĤом
    0.06
    ä¸Ģéłħ
    0.06
    à¸Ľà¸£
    0.06
    Activations Density 0.029%

    No Known Activations