© 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. 27061
    Prev
    Next
    INDEX
    Explanations

    dimensions and size

    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
    meld
    -0.08
    ÙĪÙħÙĬ
    -0.07
     hearty
    -0.07
    ä¸Ńæ¯Ĵ
    -0.07
     Whole
    -0.07
    主
    -0.07
    çĵ¦å°Ķ
    -0.06
    éĤĢ
    -0.06
    åħ¨å®¶
    -0.06
    æ¬ł
    -0.06
    POSITIVE LOGITS
     intercepted
    0.08
    尺寸
    0.08
     parall
    0.08
    -width
    0.08
    æ±ŁåĮĹ
    0.08
    мелÑĮ
    0.08
    Projected
    0.08
    尺寸çļĦ
    0.07
     grows
    0.07
    *scale
    0.07
    Activations Density 0.005%

    No Known Activations