© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19437
    Prev
    Next
    INDEX
    Explanations

    paired or assigned randomly

    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
    anak
    -0.08
    è§ĦèĮĥçļĦ
    -0.08
    åĴĮè§ĦèĮĥ
    -0.07
    mdb
    -0.07
     volumen
    -0.07
    è§ĦèĮĥæĢ§
    -0.07
    ")+
    -0.07
     dò
    -0.07
    æĶ¶èĹıåĵģ
    -0.07
    è¦ıç¯Ħ
    -0.06
    POSITIVE LOGITS
     -
    0.06
    ç»Ħ建
    0.05
    omot
    0.05
     tai
    0.05
     groups
    0.05
    å¿ħèĥľ
    0.05
     pairs
    0.05
    å¦į
    0.04
     Red
    0.04
     aster
    0.04
    Activations Density 0.035%

    No Known Activations