© 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. 4546
    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
    ront
    -0.08
    onne
    -0.07
    жай
    -0.07
    olib
    -0.07
    .inst
    -0.07
    åıĶ
    -0.07
    Marke
    -0.07
     corre
    -0.07
    ogene
    -0.07
    ernote
    -0.07
    POSITIVE LOGITS
    ãĥķãĥªãĥ¼
    0.07
    LOW
    0.07
    å¤§ä½ľæĪĺ
    0.06
    åģļ好äºĨ
    0.06
    æĸ°æĢĿè·¯
    0.06
    å¥
    0.06
    主åĬ¨æĢ§
    0.06
    cko
    0.06
    å¹²éĥ¨çļĦ
    0.06
    æľī为
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.