© 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. 19606
    Prev
    Next
    INDEX
    Explanations

    thinking and insight

    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
    ores
    -0.06
    为ä»ĸ人
    -0.05
    缼
    -0.05
    adian
    -0.05
     Gale
    -0.04
    енÑĮ
    -0.04
    å½ĵæŶçļĦ
    -0.04
     story
    -0.04
    ή
    -0.04
    æ±Ĥ
    -0.04
    POSITIVE LOGITS
    æķĻäºİ
    0.08
    quel
    0.07
    enom
    0.06
    æĢĿæĥ³å®¶
    0.06
    mati
    0.06
     اÙĦÙħÙĤبÙĦ
    0.06
    byss
    0.06
    lett
    0.06
    ingly
    0.06
    iest
    0.06
    Activations Density 0.003%

    No Known Activations