© 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. 19776
    Prev
    Next
    INDEX
    Explanations

    code delimiters

    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
    æİĸ
    -0.06
     excav
    -0.06
    æĶ¶åĽŀ
    -0.06
    ozn
    -0.06
    ocu
    -0.06
    'l
    -0.05
    TestId
    -0.05
    'o
    -0.05
    è¿ĩç¨ĭåĴĮ
    -0.05
    å¸Ĩ
    -0.05
    POSITIVE LOGITS
    igraphy
    0.06
    inherit
    0.06
    iken
    0.06
    aglia
    0.06
    arnation
    0.05
     delegate
    0.05
    affle
    0.05
    å¯Ŀ
    0.05
     delegates
    0.05
    彪
    0.05
    Activations Density 0.027%

    No Known Activations