© 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. 45558
    Prev
    Next
    INDEX
    Explanations

    geometric shapes and structures

    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
    ä¸İçİ°å®ŀ
    -0.07
     tether
    -0.07
    veill
    -0.07
    æłijä¸ĬçļĦ
    -0.06
    rone
    -0.06
    æľ
    -0.06
     causal
    -0.06
     halluc
    -0.06
     decom
    -0.06
    对人类
    -0.06
    POSITIVE LOGITS
    尺寸
    0.09
    尺寸为
    0.09
    -spacing
    0.09
    äºĮçŃī
    0.08
    宽度
    0.08
    éĶµ
    0.08
    åŀĭéĴ¢
    0.08
    mail
    0.08
    Exposed
    0.08
    设计åħ¬åı¸
    0.08
    Activations Density 0.008%

    No Known Activations