© 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. 23353
    Prev
    Next
    INDEX
    Explanations

    most common cause

    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
    è¶Ĭå°ij
    -0.07
    åĪļåĪ°
    -0.07
    minimum
    -0.07
    lep
    -0.07
    æľĢ大éĻIJ度
    -0.06
    è¶Ĭä½İ
    -0.06
    èĽĬ
    -0.06
     Minimum
    -0.06
    aldo
    -0.06
    çī¹æĸ°
    -0.06
    POSITIVE LOGITS
    次äºİ
    0.10
    åįłäºĨ
    0.10
    ä»ħ次äºİ
    0.10
    åIJįåĪĹ
    0.09
    åįłæį®äºĨ
    0.09
     ì°¨ì§Ģ
    0.09
    约åįł
    0.08
    第ä¸Ģ大
    0.08
    åįł
    0.08
     among
    0.08
    Activations Density 0.450%

    No Known Activations