© 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. 20135
    Prev
    Next
    INDEX
    Explanations

    time and timing

    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
    оÑĢоÑĤ
    -0.06
    izu
    -0.06
     steep
    -0.05
     shootout
    -0.05
    داث
    -0.05
    è¿Ŀ
    -0.05
    æĦıè¯Ĩ
    -0.05
     formats
    -0.05
    è©°
    -0.05
    al
    -0.05
    POSITIVE LOGITS
    æĹ¶æľº
    0.07
    æĻĤæ©Ł
    0.06
    opport
    0.06
    ä»Ģä¹ĪæŶåĢĻ
    0.06
    ä½ķæŶ
    0.06
     occasions
    0.06
     Timing
    0.06
     Conditions
    0.06
    æī¾ä¸ª
    0.05
    æģ°åĪ°
    0.05
    Activations Density 0.040%

    No Known Activations