© 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. 17309
    Prev
    Next
    INDEX
    Explanations

    reactive streams and observables

    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
    ç´§
    -0.06
    å¤ķ
    -0.06
    éĢıåħī
    -0.05
    æ´ĭ
    -0.05
     resolve
    -0.05
    æĻ¶çŁ³
    -0.05
    æİĴæ³Ħ
    -0.05
    解æŀIJ
    -0.05
     sunrise
    -0.05
    毫
    -0.05
    POSITIVE LOGITS
    æĸ¹ç®¡
    0.06
    uner
    0.06
     Pipes
    0.05
    ugel
    0.05
    صÙģ
    0.05
     Bryant
    0.05
     Levy
    0.05
    uson
    0.05
     weren
    0.05
    bron
    0.05
    Activations Density 0.037%

    No Known Activations