© 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. 17941
    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
    orte
    -0.05
    åħĪåľ¨
    -0.05
    åİŁå®ļ
    -0.05
    ä¼¼æĺ¯
    -0.05
    æŀIJ
    -0.05
     dual
    -0.04
    aber
    -0.04
    æŶèĩ³
    -0.04
    bn
    -0.04
    æĵĤ
    -0.04
    POSITIVE LOGITS
    edom
    0.06
    äºĪ
    0.06
    ç¾ŀ
    0.06
    NewLabel
    0.06
    thic
    0.06
    боÑĢÑĭ
    0.06
    åIJĽ
    0.06
    modern
    0.06
     warmly
    0.06
    çĽ¾
    0.05
    Activations Density 0.000%

    No Known Activations