© 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. 20362
    Prev
    Next
    INDEX
    Explanations

    section identifier

    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
    å¿ĺ
    -0.05
    ÙĪست
    -0.05
    emer
    -0.05
    ×ķף
    -0.05
    群ç»Ħ
    -0.05
    横æī«
    -0.05
    æľĢåĢ¼å¾Ĺ
    -0.05
    ований
    -0.05
    irii
    -0.05
    metric
    -0.05
    POSITIVE LOGITS
     say
    0.06
    è¿«
    0.06
    лоÑĤ
    0.05
     cvs
    0.05
     apa
    0.05
    æĹ©æ³Ħ
    0.05
    ä¸Ĭ车
    0.05
    ervers
    0.05
    ัà¸ļ
    0.05
    åĪ»
    0.05
    Activations Density 0.004%

    No Known Activations