© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17836
    Prev
    Next
    INDEX
    Explanations

    film, novel, or story, often directed

    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
    aran
    -0.06
     sort
    -0.06
    gmt
    -0.06
    adakan
    -0.05
     sorts
    -0.05
     emb
    -0.05
    ä¸ĭä¸Ģ次
    -0.05
     vez
    -0.05
    çĹħæĤ£èĢħ
    -0.05
    ذاب
    -0.05
    POSITIVE LOGITS
    stoff
    0.06
    icter
    0.06
    äºĮ个
    0.06
    ogen
    0.05
    æĪijè¿Ļ个
    0.05
    Å¡ÃŃ
    0.05
    橱
    0.05
    大æīĵ
    0.05
     ÑĩаÑģÑĤиÑĩ
    0.05
    лоÑģÑı
    0.05
    Activations Density 0.003%

    No Known Activations