© 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. 19524
    Prev
    Next
    INDEX
    Explanations

    purpose words (objective, aim, goal)

    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
    以确ä¿Ŀ
    -0.06
    以ä¿Ŀè¯ģ
    -0.06
    以åĪ©
    -0.05
    æľĢç»ĪçļĦ
    -0.05
    ä¸ĭæĦıè¯ĨçļĦ
    -0.05
     ÑĩÑĤобÑĭ
    -0.05
    以便äºİ
    -0.05
    emax
    -0.05
    以ä¿ĿæĮģ
    -0.05
     Äijá»ĥ
    -0.05
    POSITIVE LOGITS
    кла
    0.06
    uft
    0.05
    fts
    0.05
     Consultez
    0.05
     cornerback
    0.05
     -:
    0.05
     relevant
    0.05
    -specific
    0.05
    æĺ¯ä½łçļĦ
    0.05
     اÙĦÙħØŃتÙħ
    0.05
    Activations Density 0.002%

    No Known Activations