© 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. 10751
    Prev
    Next
    INDEX
    Explanations

    specialized modifications, adaptation, and additions

    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
     unm
    -0.08
    rians
    -0.08
     assegn
    -0.07
     arbitrarily
    -0.07
    aiss
    -0.07
     ngẫu
    -0.06
     improves
    -0.06
    èī¯æĢ§
    -0.06
    ä¾Ŀ
    -0.06
    ìħĢ
    -0.06
    POSITIVE LOGITS
    ä¸ĵéŨçļĦ
    0.14
     adaptations
    0.14
     adapted
    0.13
    ä¸ĵéĹ¨ä¸º
    0.13
    ä¸ĵéŨ
    0.13
     specialized
    0.13
    å°ĪéĸĢ
    0.12
    éĢĤåºĶ
    0.12
     accordingly
    0.12
     special
    0.12
    Activations Density 0.318%

    No Known Activations