© 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. 16822
    Prev
    Next
    INDEX
    Explanations

    rows

    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
    kons
    -0.06
    garan
    -0.06
    usra
    -0.06
    ÑģполÑĮз
    -0.06
    æ²Ļæ²Ļ
    -0.06
    åĪ¶ç¨ĭ
    -0.06
     malu
    -0.06
    主å§Ķ
    -0.05
    éĢļè´§
    -0.05
    andar
    -0.05
    POSITIVE LOGITS
    tings
    0.06
    çļĦæĹ¥åŃIJ
    0.05
    adir
    0.05
    иÑģка
    0.05
    emento
    0.05
     routine
    0.05
    ados
    0.05
    empt
    0.05
     pictured
    0.05
    å¤ļãģĦãģ§ãģĻ
    0.05
    Activations Density 0.008%

    No Known Activations