© 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. 2253
    Prev
    Next
    INDEX
    Explanations

    Australian history

    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
    çļĦæīĭä¸Ń
    -0.07
     оÑĤзÑĭва
    -0.06
     Posted
    -0.06
     ultimately
    -0.06
    çļĦåĽłç´ł
    -0.06
    roma
    -0.06
    jeta
    -0.06
    ä¸Ķä¸į
    -0.06
    ä½İ端
    -0.06
    å¼ķ
    -0.06
    POSITIVE LOGITS
    çŃīåĨħ容
    0.10
    为é¢ĺ
    0.09
    ä¸Ģ缮äºĨçĦ¶
    0.09
     ÙĪعÙĨ
    0.08
     подÑĢобно
    0.08
     topics
    0.08
    åıĬåħ¶
    0.08
     details
    0.08
     minut
    0.08
    åİĨåİĨ
    0.08
    Activations Density 0.475%

    No Known Activations