© 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. 20432
    Prev
    Next
    INDEX
    Explanations

    circular, around, central

    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
    tures
    -0.09
     condizion
    -0.08
    yles
    -0.08
    atomy
    -0.08
    層次
    -0.08
    hd
    -0.07
    enso
    -0.07
    ä¸Ģæł·äºĨ
    -0.07
    tick
    -0.07
    ä¸Ģ亮
    -0.07
    POSITIVE LOGITS
    æīĢéľĢçļĦ
    0.07
    ror
    0.07
    aju
    0.07
    åĬłéĢŁåº¦
    0.07
    vasive
    0.07
    needed
    0.07
    å®īåħ¨å·¥ä½ľ
    0.07
     acceleration
    0.07
    required
    0.07
    å¿ħå¤ĩçļĦ
    0.07
    Activations Density 0.001%

    No Known Activations