© 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. 14942
    Prev
    Next
    INDEX
    Explanations

    bad or poor quality

    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
     fullest
    -0.09
     hopefully
    -0.09
    aug
    -0.08
    alue
    -0.08
     presumably
    -0.08
    rome
    -0.07
    auen
    -0.07
    åħ¶ä¹IJ
    -0.07
    åIJĦ个é¢ĨåŁŁ
    -0.07
    oline
    -0.07
    POSITIVE LOGITS
    缺ä¹ı
    0.15
     lack
    0.14
    lack
    0.13
     inadequate
    0.12
     insufficient
    0.12
    缺å°ij
    0.12
    æľªåıĬæŶ
    0.11
     Lack
    0.11
     improperly
    0.10
     poor
    0.10
    Activations Density 0.147%

    No Known Activations