© 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. 61478
    Prev
    Next
    INDEX
    Explanations

    connecting things together

    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
    æĢģ
    -0.07
    èķ´
    -0.07
    åĿ
    -0.06
    æĽ¾
    -0.06
     streaming
    -0.06
     hij
    -0.06
    åĬ«
    -0.06
     Cool
    -0.06
    ä¹Ŀ大
    -0.06
    æ¼ł
    -0.06
    POSITIVE LOGITS
    è§ĦèĮĥè¦ģæ±Ĥ
    0.10
    SPAN
    0.09
    è¡ĮéĹ´
    0.09
    å°ıå¹³
    0.09
    å¤ĸ侧
    0.09
     perpendicular
    0.09
     protr
    0.08
    ffit
    0.08
    æIJŃæİ¥
    0.08
    æĥ³çŁ¥éģĵçļĦçŃĶæ¡Ī
    0.08
    Activations Density 0.072%

    No Known Activations