© 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. 46723
    Prev
    Next
    INDEX
    Explanations

    complexities and nuances

    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
     consec
    -0.08
    寸
    -0.06
     physically
    -0.06
     indirectly
    -0.06
    çļĦåŁºæľ¬è¦ģæ±Ĥ
    -0.06
     consecutive
    -0.06
    åŁºæľ¬è¦ģæ±Ĥ
    -0.06
    å¿ħé¡»åħĪ
    -0.06
     phys
    -0.06
     Phys
    -0.06
    POSITIVE LOGITS
    å¤įæĿĤæĢ§
    0.12
     nuanced
    0.12
     nu
    0.10
    å¤ļæł·
    0.10
    Nu
    0.10
    å¤įæĿĤçļĦ
    0.09
    è¤ĩ鼾
    0.09
     individual
    0.09
    å¤ļæł·çļĦ
    0.09
     complexity
    0.09
    Activations Density 0.061%

    No Known Activations