© 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. 46741
    Prev
    Next
    INDEX
    Explanations

    without -ing words

    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
    ä¸įèĥ½ä½ľä¸º
    -0.07
    urd
    -0.06
     yes
    -0.06
     both
    -0.06
    expired
    -0.06
    èĻ½æľī
    -0.06
    iller
    -0.06
    æĹłè®º
    -0.06
    Õ¸ÖĢ
    -0.06
    rane
    -0.06
    POSITIVE LOGITS
     resort
    0.09
    æĺ¯ä¸įæĺ¯å¾Ī
    0.08
    jaw
    0.08
    APPED
    0.07
    äºļäºİ
    0.07
    çļĦä¸Ģå¥Ĺ
    0.07
    epen
    0.07
     recourse
    0.07
    aneously
    0.07
    ùn
    0.07
    Activations Density 0.066%

    No Known Activations