© 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. 34587
    Prev
    Next
    INDEX
    Explanations

    facilitates, sufficient, required, favor

    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
    æĭĸç´¯
    -0.08
    æı©
    -0.07
    anjang
    -0.07
     Inherits
    -0.06
    acher
    -0.06
    ä¼ļéļıçĿĢ
    -0.06
    æķĻèĤ²å®ŀ践活åĬ¨
    -0.06
    åıĬåħ¶
    -0.06
    å½ĵåħ¶
    -0.06
     IDisposable
    -0.06
    POSITIVE LOGITS
    åħ¨éĥ¨è¯Ħ论
    0.09
    æĤ¨çİ°åľ¨çļĦä½įç½®
    0.08
    ä¿ĥ使
    0.08
    åĪ©äºİ
    0.08
    对ä¸Ĭè¿°
    0.07
    .tom
    0.07
    游åŃIJ
    0.07
    betrieb
    0.07
     firstly
    0.07
    å°Ĩæľī
    0.07
    Activations Density 0.071%

    No Known Activations