© 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. 18521
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ãģĹãģĭ
    -0.05
     fork
    -0.05
    à¸IJาà¸Ļ
    -0.05
     sanity
    -0.05
    ç®Ģ称
    -0.05
    ç»Ĵ
    -0.05
     fer
    -0.05
     pat
    -0.05
     isolation
    -0.04
     pang
    -0.04
    POSITIVE LOGITS
    ahrain
    0.06
    ctal
    0.06
    antom
    0.06
    ä½ľåĵģåĨħ容
    0.06
    æ¥ŃçķĮ
    0.06
    åįİåºŃ
    0.06
    èĭijå°ıåĮº
    0.06
    jÃŃ
    0.06
     roup
    0.06
    ohn
    0.06
    Activations Density 0.000%

    No Known Activations