© 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. 16951
    Prev
    Next
    INDEX
    Explanations

    remarkable, striking, incredible, heroic, cool, marvel, fascinating

    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
    å¿ħè¦ģçļĦ
    -0.08
    ãģĤãģı
    -0.08
     molest
    -0.07
    oy
    -0.07
    åıijæĦģ
    -0.07
    upu
    -0.07
    éĩįçĤ¹
    -0.07
    daq
    -0.07
    defs
    -0.07
     ÙĥاÙģ
    -0.07
    POSITIVE LOGITS
    ä¹ĭå¤Ħåľ¨äºİ
    0.09
    ç»Ŀ伦
    0.08
    级çļĦ
    0.08
    æĿ°ä½ľ
    0.08
    å±ħçĦ¶
    0.07
     remarkable
    0.07
     feats
    0.07
     Remark
    0.07
    Remark
    0.07
     astonishing
    0.07
    Activations Density 0.345%

    No Known Activations