© 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. 14546
    Prev
    Next
    INDEX
    Explanations

    landscape painter, architecture, or portraits

    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
    æĹºçĽĽ
    -0.08
    åľ°ä¸ĭ室
    -0.07
    úst
    -0.07
    çĤ«éħ·
    -0.07
    æĹłéĹ»
    -0.07
    ENCH
    -0.07
    eworthy
    -0.07
    istet
    -0.07
    PTR
    -0.07
    #index
    -0.06
    POSITIVE LOGITS
    å¦ĤçĶ»
    0.10
     scenery
    0.10
    æĻ¯èī²
    0.10
    ä¸Ģå¹ħ
    0.10
    åľ°è²Į
    0.09
    æĺİä¿¡çīĩ
    0.08
    å®ľ
    0.08
    åĨĻçĶŁ
    0.08
    é£İæĻ¯
    0.08
    å®ľäºº
    0.08
    Activations Density 0.036%

    No Known Activations