© 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. 50272
    Prev
    Next
    INDEX
    Explanations

    x after _ or b

    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
    anea
    -0.07
    ä¸ĢèģĮ
    -0.07
    éĤģ
    -0.07
     доÑģ
    -0.06
    çĮ®è¡Ģ
    -0.06
    ãĥ¼ãĥĪãĥ«
    -0.06
    ÙĤÙģ
    -0.06
    mini
    -0.06
    iché
    -0.06
    æ¯ıéĢ¢
    -0.06
    POSITIVE LOGITS
     اÙĦØ«ÙĦاثة
    0.08
    uste
    0.08
    aption
    0.08
    姿
    0.07
    缺ä¸Ģ
    0.07
    çħĮ
    0.07
    ãĥ³ãĥĹ
    0.07
    ignum
    0.07
     Triple
    0.07
    chy
    0.07
    Activations Density 0.006%

    No Known Activations