© 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. 10767
    Prev
    Next
    INDEX
    Explanations

    place names or personal names

    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
    aiser
    -0.08
    amel
    -0.08
    èī²åĪĹ
    -0.07
    ãĥªãĥ³ãĤ°
    -0.07
    ableObject
    -0.07
    å¦Ĩ
    -0.07
    å²Ĺä½įä¸Ĭ
    -0.07
    wiat
    -0.07
     settling
    -0.07
     ãĥĪãĥĥãĥĹãĥļãĥ¼ãĤ¸
    -0.07
    POSITIVE LOGITS
    åŃŁåŃIJ
    0.09
    æ¢ģ
    0.08
    汤
    0.07
     Birmingham
    0.07
    ç¥ł
    0.06
    ä¹ī
    0.06
    大ä¹ī
    0.06
    çĥŃ
    0.06
    alan
    0.06
    æļij
    0.06
    Activations Density 0.001%

    No Known Activations