© 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. 46521
    Prev
    Next
    INDEX
    Explanations

    learning and training

    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
    ospace
    -0.08
    creat
    -0.07
    éĥ½å¸Ĥå°ı说
    -0.07
     dÃ¼ÅŁÃ¼n
    -0.07
    ujur
    -0.07
    _invite
    -0.07
    åѦçĶŁå®¿èĪį
    -0.07
    _ASM
    -0.07
     undermin
    -0.07
     convo
    -0.07
    POSITIVE LOGITS
     learning
    0.13
     acquired
    0.11
    çļĦåŃ¦ä¹ł
    0.11
     training
    0.11
     learn
    0.10
    è®Ńç»ĥ
    0.10
     apprend
    0.10
    learning
    0.10
    -learning
    0.10
    learn
    0.10
    Activations Density 0.118%

    No Known Activations