© 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. 18650
    Prev
    Next
    INDEX
    Explanations

    plans, wants, holding

    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
    irman
    -0.07
    мееÑĤÑģÑı
    -0.06
    intes
    -0.06
    YPE
    -0.06
     ÙħجÙĩ
    -0.06
    orsa
    -0.06
    aved
    -0.06
    uras
    -0.06
     ÐĺÑģÑĤо
    -0.06
     laps
    -0.06
    POSITIVE LOGITS
    åĪļ好
    0.06
    æį¢
    0.06
     доÑģÑĤ
    0.06
    ä½įæķ°
    0.06
    æł¡
    0.06
     growth
    0.05
     “
    0.05
    rowth
    0.05
    åĩĢ
    0.05
    æģ°å¥½
    0.05
    Activations Density 0.142%

    No Known Activations