© 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. 19754
    Prev
    Next
    INDEX
    Explanations

    sexuality and identity

    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
     clit
    -0.06
    amic
    -0.05
    Å¡em
    -0.05
    letz
    -0.05
    اش
    -0.05
    reon
    -0.05
    ÑĪли
    -0.05
    uchy
    -0.05
    欣欣
    -0.05
     ÙĩØ´
    -0.05
    POSITIVE LOGITS
     Churchill
    0.06
    ibilmente
    0.06
    åѦçĶŁä»¬
    0.06
     Mats
    0.05
    éĶĢåĶ®éĩı
    0.05
    马æĭī
    0.05
    depart
    0.05
     distances
    0.05
    åĴĮ责任
    0.05
    alj
    0.05
    Activations Density 0.005%

    No Known Activations