© 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. 22286
    Prev
    Next
    INDEX
    Explanations

    video games and media titles

    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
    gaz
    -0.08
    ä¸įåºĶæ±Ĥ
    -0.06
    continu
    -0.06
    [strlen
    -0.06
    quen
    -0.06
    angu
    -0.06
    ç¢Į
    -0.06
    éĺ¶
    -0.06
    ç´°
    -0.06
    庵
    -0.06
    POSITIVE LOGITS
    æĻĤåįĬ
    0.06
    æĸĩèīº
    0.06
    åı¯åĸľ
    0.06
    Vict
    0.06
     Vict
    0.05
     fashion
    0.05
     Birmingham
    0.05
    转åĮĸ
    0.05
     coll
    0.05
     charged
    0.05
    Activations Density 0.013%

    No Known Activations