© 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. 22254
    Prev
    Next
    INDEX
    Explanations

    protocol

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ansk
    -0.06
    ãģ¾ãģ¾ãģ§
    -0.05
    æĹłå®³
    -0.05
    ستÙĨ
    -0.05
    onnées
    -0.05
     risky
    -0.05
    ä¸īåĮħ
    -0.05
    alous
    -0.05
    æĩ¸åij½
    -0.05
     firme
    -0.05
    POSITIVE LOGITS
    羣æŃ£æĦıä¹īä¸ĬçļĦ
    0.06
    åı²ä¸ĬæľĢ
    0.06
    empor
    0.06
    å·¥ä½ľä¸ĬçļĦ
    0.06
     Ty
    0.06
    ificant
    0.06
    宽é«ĺ
    0.06
    éķIJ
    0.06
     bew
    0.05
    ä¸Ģæĭį
    0.05
    Activations Density 0.090%

    No Known Activations