© 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. 57378
    Prev
    Next
    INDEX
    Explanations

    .width or .getDate syntax

    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
    {'
    -0.07
     Tore
    -0.07
    äºĨåħ¶
    -0.06
    åŃIJæĺ¯
    -0.06
    ala
    -0.06
    è¿Ľä¸ĢæŃ¥åıijå±ķ
    -0.06
    å±ķçİ°åľ¨
    -0.06
    lach
    -0.06
    天éŃĶ
    -0.06
    åħīæĺ¯
    -0.06
    POSITIVE LOGITS
    çļĦä¸ĢåįĬ
    0.13
    ä¸īåĪĨä¹ĭä¸Ģ
    0.12
    ä¸īåĪĨä¹ĭäºĮ
    0.10
    çĻ¾åĪĨä¹ĭ
    0.09
     بÙĨسبة
    0.08
    ä¸ĢåįĬ
    0.08
    ä¸īæĪIJ
    0.08
    åĽĽåĪĨä¹ĭä¸Ģ
    0.08
    åįĬæķ°
    0.08
    jee
    0.08
    Activations Density 0.008%

    No Known Activations