© 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. 19188
    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
    ãģľãĤĵ
    -0.07
    otor
    -0.07
    æݢ索åĴĮ
    -0.07
    bern
    -0.07
    arily
    -0.07
    aqu
    -0.06
    Ứ
    -0.06
    á»iji
    -0.06
    æĿ¡ä»¶æĺ¯
    -0.06
    bero
    -0.06
    POSITIVE LOGITS
     specific
    0.06
    æ³ķ
    0.05
    éĻIJ
    0.05
     sclerosis
    0.05
    åħ·ä½ĵ
    0.05
    æ´¾
    0.05
     individual
    0.05
    åįģåŃĹ
    0.05
    0.05
    é«ĺ
    0.05
    Activations Density 0.000%

    No Known Activations