© 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. 19668
    Prev
    Next
    INDEX
    Explanations

    code file extensions

    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
    ayout
    -0.06
    akarta
    -0.06
    apun
    -0.06
    Ĩ
    -0.06
    apura
    -0.06
     regia
    -0.06
    еÑģÑģи
    -0.06
    ä¸ĢèģĬ
    -0.06
    tuu
    -0.06
    ÑģмоÑĤÑĢиÑĤе
    -0.06
    POSITIVE LOGITS
    Âł
    0.08
    âĢ
    0.06
    ...
    0.06
    0.06
    ä½į
    0.05
    âĢ¦
    0.05
    bit
    0.05
    人çī©
    0.05
    ³³
    0.05
    æİĮ
    0.05
    Activations Density 0.077%

    No Known Activations