© 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. 34222
    Prev
    Next
    INDEX
    Explanations

    temperature, November, age, distribution

    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
    æ°ı
    -0.07
    minister
    -0.06
    åħľ
    -0.06
    Thu
    -0.06
    æ½ľåľ¨
    -0.06
    èī°
    -0.06
    å·
    -0.06
    zam
    -0.06
    è±ļ
    -0.06
     Dunk
    -0.06
    POSITIVE LOGITS
    çĽ¸å¯¹åºĶçļĦ
    0.09
    Õ¡Õ¿
    0.08
    对åºĶçļĦ
    0.08
    èĭ¦
    0.08
     voce
    0.08
    ERSIST
    0.08
    èĢĮä¸įè§ģ
    0.08
    adier
    0.07
    汹汹
    0.07
    æŁ¥æŁ¥
    0.07
    Activations Density 0.020%

    No Known Activations