© 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. 1064
    Prev
    Next
    INDEX
    Explanations

    up to

    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
    俱ä¹IJéĥ¨
    -0.09
    å½°åĮĸ
    -0.07
    åĭĩå¾Ģ缴åīį
    -0.07
    æĸ°åĬłåĿ¡
    -0.07
    äºĮåįģåĽĽ
    -0.07
    åĬłæĭ¿å¤§
    -0.07
    çļĦèĮĥåĽ´
    -0.06
    ä¹ĭéķ¿
    -0.06
     aff
    -0.06
    _INITIALIZER
    -0.06
    POSITIVE LOGITS
     fewer
    0.11
    è¯ģæį®è¯ģæĺİ
    0.09
    '](
    0.09
    種é¡ŀãģ®
    0.08
    æĸ¹å¼ı使çĶ¨
    0.08
    è·¯åħ¬äº¤è½¦
    0.08
    ()%
    0.08
     demasi
    0.07
    ãĤ¿ãĤ¤ãĥĹãģ®
    0.07
    /{}/
    0.07
    Activations Density 0.314%

    No Known Activations