© 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. 61916
    Prev
    Next
    INDEX
    Explanations

    adding or making something

    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
    hide
    -0.06
    ingen
    -0.06
     fac
    -0.06
    人è´Ńä¹°
    -0.06
    è¦ģä¿ĿæĮģ
    -0.06
    åľ¨è¿Ľåħ¥
    -0.06
    çķªå¤ĸ
    -0.06
    产åĵģéĶĢåĶ®
    -0.06
    åĬĽæ±Ĥ
    -0.06
     (
    -0.06
    POSITIVE LOGITS
    å¾Ĺ天
    0.09
    ãĥĻãĤ¤
    0.08
    áĥĽáĥIJ
    0.08
    ocache
    0.08
    åĩ«
    0.08
    è¶ħåĩ¡
    0.08
    /frame
    0.08
    (iOS
    0.08
    缸åħ³æ³ķå¾ĭ责任
    0.07
    rames
    0.07
    Activations Density 0.234%

    No Known Activations