© 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. 64222
    Prev
    Next
    INDEX
    Explanations

    ways to improve things

    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
    oir
    -0.08
    κÏį
    -0.07
    çĶļ
    -0.07
    æķħèĢĮ
    -0.07
    Whilst
    -0.07
    Util
    -0.07
     utilized
    -0.07
    并éĿŀæĺ¯
    -0.06
    æ¯ĭ庸
    -0.06
     aforementioned
    -0.06
    POSITIVE LOGITS
    eful
    0.11
    éĥ½æ²¡
    0.10
    æ°´éĩĮ
    0.09
    宫éĩĮ
    0.09
    ä¹Łæ²¡
    0.09
    egen
    0.08
    ustin
    0.08
    edy
    0.08
    åѦèĭ±è¯Ń
    0.08
    egl
    0.08
    Activations Density 0.694%

    No Known Activations