© 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. 38040
    Prev
    Next
    INDEX
    Explanations

    åħĪåľ¨

    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
    æĽ´æĸ°èĩ³
    -0.07
    ä¸ĢçĻ¾å¹´
    -0.07
    继ç»Ńä¿ĿæĮģ
    -0.07
    åıĪéģĵ
    -0.06
    ä¸Ģç»Ħ
    -0.06
    è¿Ļä¸ĸçķĮ
    -0.06
    æĶ¾çľ¼
    -0.06
    建æĸ°
    -0.06
    okes
    -0.06
     Pach
    -0.06
    POSITIVE LOGITS
    å¿ħé¡»åħĪ
    0.13
    åħĪåľ¨
    0.11
    åħĪåİ»
    0.11
    äºĭåīį
    0.11
    éľĢè¦ģæıIJåīį
    0.11
    æĵįä½ľæµģç¨ĭ
    0.10
    缴æİ¥ä»İ
    0.10
    æĺ¯åħĪ
    0.10
    åħĪåĪ°
    0.10
    缴æİ¥è¿Ľåħ¥
    0.10
    Activations Density 0.290%

    No Known Activations