© 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. 15059
    Prev
    Next
    INDEX
    Explanations

    conditional checks

    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
    rame
    -0.08
    好åѦçĶŁ
    -0.07
    åºĶåħ·æľī
    -0.06
    å®ĥå°Ĩ
    -0.06
    askell
    -0.06
    åħ¶è§ĤçĤ¹
    -0.06
    好èĩªå·±çļĦ
    -0.06
    andon
    -0.06
    PI
    -0.06
    æľīåħ³äºİ
    -0.06
    POSITIVE LOGITS
     downright
    0.08
    åĥıä½ł
    0.08
     sebaliknya
    0.08
    åıįä¹ĭ
    0.08
     otherwise
    0.08
    åħ¶ä»ĸæĸ¹å¼ı
    0.08
    åĥıæĪij
    0.08
    vie
    0.08
     juist
    0.07
    ICC
    0.07
    Activations Density 0.017%

    No Known Activations