© 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. 19101
    Prev
    Next
    INDEX
    Explanations

    destructor or defer action

    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
    uno
    -0.05
    иж
    -0.05
    æݨ
    -0.05
    /id
    -0.05
    une
    -0.05
     Id
    -0.05
    ta
    -0.05
     id
    -0.05
    ola
    -0.05
    uma
    -0.05
    POSITIVE LOGITS
    iep
    0.06
    áĢĬáĢº
    0.06
    kait
    0.06
    ieben
    0.06
    oskop
    0.06
     تصر
    0.06
    纳士
    0.06
    etrie
    0.06
    etimes
    0.06
    skal
    0.06
    Activations Density 0.002%

    No Known Activations