© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22321
    Prev
    Next
    INDEX
    Explanations

    main computer, graph, DNA, daughter, transition, tuples, Nev, collapse

    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
    æľīé«ĺ
    -0.07
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.07
    çīĩçīĩ
    -0.06
    è½¬çľ¼
    -0.06
    åĴĮä¸į
    -0.06
    æľīä¸Ń
    -0.06
    azine
    -0.06
    æĥħçļĦ
    -0.06
    æĪijåij¢
    -0.06
    çļĦä¸įèī¯
    -0.06
    POSITIVE LOGITS
    ç±»
    0.06
    åİī
    0.05
    ãĢģ
    0.05
    ç½®
    0.05
    ahr
    0.05
    åĪĻ
    0.05
    inqu
    0.05
    èĢĮè¨Ģ
    0.05
     modest
    0.05
    “
    0.05
    Activations Density 0.199%

    No Known Activations