© 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. 17274
    Prev
    Next
    INDEX
    Explanations

    sometimes, often

    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
     presumably
    -0.08
    èĥ½å¤ŁæľīæķĪ
    -0.07
     ÑıкобÑĭ
    -0.07
     already
    -0.07
     reportedly
    -0.06
    ÏĦÏģια
    -0.06
    èĥ½å¤ŁæĽ´å¥½åľ°
    -0.06
    éĩĩçĶ¨äºĨ
    -0.06
    对该
    -0.06
    å°Ĩè¿Ļ
    -0.06
    POSITIVE LOGITS
    ometimes
    0.09
    æľīæŶåĢĻ
    0.09
    人æĪĸ
    0.09
     бÑĭваеÑĤ
    0.09
    Often
    0.09
    Sometimes
    0.09
    å¾Ģå¾Ģæĺ¯
    0.09
     поÑĢой
    0.08
     sometimes
    0.08
    æľīæĻĤ
    0.08
    Activations Density 0.001%

    No Known Activations