© 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. 33963
    Prev
    Next
    INDEX
    Explanations

    PET, method, sed, EC, generics, framework, sort

    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
    Ģ
    -0.07
    æĭĭ
    -0.07
    æĬĸ
    -0.07
    åĢįçļĦ
    -0.07
    osci
    -0.07
    jero
    -0.07
     tez
    -0.07
    åĽĬ
    -0.06
    راء
    -0.06
    ezer
    -0.06
    POSITIVE LOGITS
    WithValue
    0.08
    å¤ļ次
    0.07
    ساب
    0.07
    ®,
    0.07
    å¹¿æ³ĽçĶ¨äºİ
    0.07
    pts
    0.07
     Trick
    0.07
    LocalizedString
    0.07
    æĪijæľīä¸Ģ个
    0.07
    ÏĢλα
    0.06
    Activations Density 0.057%

    No Known Activations