© 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. 21005
    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
     float
    -0.06
    dro
    -0.06
    ç»ı
    -0.05
    çļĦèĤī
    -0.05
    nant
    -0.05
     hoffe
    -0.05
    oding
    -0.05
    aj
    -0.05
     Pey
    -0.05
    æĤ¬æµ®
    -0.05
    POSITIVE LOGITS
    encontre
    0.06
     лежа
    0.06
    ises
    0.06
    ÑģÑĤÑĢе
    0.06
    ÙĬض
    0.06
    segue
    0.06
    éĥ¨ä¸ĭ
    0.06
    äºĭçī©
    0.06
     PURPOSE
    0.06
     gola
    0.06
    Activations Density 0.000%

    No Known Activations