© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15884
    Prev
    Next
    INDEX
    Explanations

    begin, become, blossom, slow, drawn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IBIL
    -0.08
    Immediately
    -0.08
    ç«ĭåį³
    -0.08
     Immediately
    -0.08
    åį³åĪ»
    -0.08
     immediately
    -0.07
     instantly
    -0.07
    çŀ¬éĹ´
    -0.07
    Instant
    -0.07
     Instant
    -0.07
    POSITIVE LOGITS
    éĢIJæ¸IJæĪIJ为
    0.18
    æ¸IJæ¸IJ
    0.17
    æ¸IJæ¸IJçļĦ
    0.17
     dần
    0.17
    éĢIJæ¸IJ
    0.17
     gradually
    0.16
     eventually
    0.15
    è¶ĬæĿ¥è¶Ĭå¤ļçļĦ
    0.15
    æ¸IJæ¸IJåľ°
    0.15
     تدرÙĬ
    0.15
    Activations Density 0.227%

    No Known Activations