© 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. 57128
    Prev
    Next
    INDEX
    Explanations

    seconds and minutes

    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
    urat
    -0.08
    è¿ŀå¤ľ
    -0.08
    imana
    -0.07
    ç±ģ
    -0.07
     eventual
    -0.07
    åįĬå¤ľ
    -0.07
     Months
    -0.07
    azon
    -0.07
    æķ°æľĪ
    -0.07
    æĹ¥åŃIJ
    -0.07
    POSITIVE LOGITS
    ä¸ĢåĪĨéĴŁ
    0.10
     duration
    0.10
    ç§ĴéĴŁ
    0.10
    çŁŃæļĤçļĦ
    0.09
    çŁŃæļĤ
    0.09
     durations
    0.09
    åĪĨéĴŁ
    0.09
    ä¸īåĪĨéĴŁ
    0.09
     minute
    0.09
    äºĶåĪĨéĴŁ
    0.09
    Activations Density 0.109%

    No Known Activations