© 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. 37916
    Prev
    Next
    INDEX
    Explanations

    always would follow

    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
     possibly
    -0.08
     potentially
    -0.07
    大åIJĥ
    -0.07
    åįĬæĻĮ
    -0.07
    æħĮä¹±
    -0.07
    possibly
    -0.07
    åĪĿæŃ¥
    -0.07
     widespread
    -0.07
    éria
    -0.07
    ä¸Ģå¤ľ
    -0.07
    POSITIVE LOGITS
     whenever
    0.20
    æ¯ı次éĥ½
    0.18
    æ¯ıå½ĵ
    0.18
    æ¯ı次
    0.17
     Whenever
    0.17
    Whenever
    0.16
     Occasionally
    0.15
     occasionally
    0.15
     occasional
    0.15
    variably
    0.14
    Activations Density 1.123%

    No Known Activations