© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 33717
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    REQUIRED
    -0.09
    ula
    -0.08
    enk
    -0.07
    tl
    -0.07
    _REQUIRED
    -0.07
     заÑģе
    -0.07
    Æ°á»Ŀn
    -0.07
    ä¸ĥä¸Ģ
    -0.07
    èĿł
    -0.07
    _pair
    -0.07
    POSITIVE LOGITS
    ä¸įæ¶īåıĬ
    0.12
     reversible
    0.10
    versible
    0.09
     temporary
    0.09
    ä¸įæĶ¹
    0.08
    çİ°æľī
    0.08
    ä»ĸåıªæĺ¯
    0.08
     existing
    0.08
    æĹłæįŁ
    0.08
     harmless
    0.08
    Activations Density 0.045%

    No Known Activations