© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19495
    Prev
    Next
    INDEX
    Explanations

    function method return and results

    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
    onica
    -0.07
    ifah
    -0.07
    omal
    -0.07
    èĢĮä¸įè§ģ
    -0.07
    aggi
    -0.07
     SharedModule
    -0.07
    ÑĤеÑĢи
    -0.06
    ÑĢÑıз
    -0.06
    ()."
    -0.06
    rale
    -0.06
    POSITIVE LOGITS
    (
    0.06
    put
    0.05
     put
    0.05
    æŁĦ
    0.05
     resulting
    0.05
    '
    0.04
     puts
    0.04
    çŃ¹
    0.04
    åŀĴ
    0.04
    èľĢ
    0.04
    Activations Density 0.006%

    No Known Activations