© 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. 60161
    Prev
    Next
    INDEX
    Explanations

    legal cases and procedures

    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
    rams
    -0.08
    ä¸įæĢķ
    -0.08
     nonzero
    -0.07
    å¤ļéĩį
    -0.07
    IsValid
    -0.07
    isht
    -0.07
    yai
    -0.07
    åĪ¤å®ļ
    -0.07
    æľĢè¿ijæĽ´æĸ°
    -0.06
    Convertible
    -0.06
    POSITIVE LOGITS
     expressly
    0.11
    æĹ¢çĦ¶
    0.09
    æĹ¢çĦ¶æĺ¯
    0.08
    æĹ¢çĦ¶å¦ĤæѤ
    0.08
    éħįå¥Ĺ
    0.08
    éĩij马
    0.07
    主åĬ¨ä½ľä¸º
    0.07
     enumerated
    0.07
     substantive
    0.07
    ä¹ĭ缮çļĦ
    0.07
    Activations Density 0.018%

    No Known Activations