© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19903
    Prev
    Next
    INDEX
    Explanations

    in, by, to, from, using

    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
    èĥ½åĬĽåĪĨæŀIJ
    -0.06
    conse
    -0.06
    çļĦ大éĩı
    -0.06
     !**
    -0.05
    ollywood
    -0.05
    epass
    -0.05
    é³Į
    -0.05
    ulu
    -0.05
    tui
    -0.05
    ernen
    -0.05
    POSITIVE LOGITS
    è¿ĺæĺ¯åľ¨
    0.06
    åħį
    0.06
    æĻº
    0.05
    äºij
    0.05
    åĽ½å®¶å¯¹
    0.05
    ies
    0.05
    åĽ½äº§
    0.05
    imer
    0.05
     pha
    0.05
     cer
    0.05
    Activations Density 0.002%

    No Known Activations