© 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. 16923
    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
    éŀ
    -0.06
    çľĭçľĭåIJ§
    -0.06
    ä½Ĩä¸į
    -0.06
    änger
    -0.05
    é£
    -0.05
    è¯ķè¯ķåIJ§
    -0.05
    èµ·æĿ¥åIJ§
    -0.05
    ê·¹
    -0.05
    è°Īè°Ī
    -0.05
    ä½Ĩæĺ¯æ²¡æľī
    -0.05
    POSITIVE LOGITS
    OTP
    0.07
    porn
    0.07
    工夫
    0.05
    æĹ¥æŃ¢
    0.05
    æĹłéĹ»
    0.05
    åĥı
    0.05
    äºĨåij¢
    0.05
    orno
    0.05
    åĥıä¸Ģ个
    0.05
    VPN
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.