© 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. 42356
    Prev
    Next
    INDEX
    Explanations

    parentheticals containing names or parameters

    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
    ittle
    -0.07
     Herrn
    -0.06
    导
    -0.06
    iglio
    -0.06
    å°Ĩ该
    -0.06
    æ³ĵ
    -0.06
    è¡Įä¸ļåĨħ
    -0.06
    yron
    -0.06
    çŃ
    -0.06
    çŁ¾
    -0.06
    POSITIVE LOGITS
    èĩªè¾¾
    0.09
    å¦Ĥæĺ¯
    0.08
    ifold
    0.08
    è¿Ļ天
    0.08
    åıĪåĪ°
    0.08
    æĶ¾åģĩ
    0.08
    ultos
    0.07
    alen
    0.07
    æĹłå°ĺ
    0.07
    zb
    0.07
    Activations Density 0.003%

    No Known Activations