© 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. 21722
    Prev
    Next
    INDEX
    Explanations

    step, configuration, platform

    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
     Fern
    -0.06
    认
    -0.06
     Say
    -0.06
    èĭ¥å¹²ä¸ª
    -0.06
    ائ
    -0.06
     Ray
    -0.06
     ext
    -0.06
    atal
    -0.06
    æŁIJä¸Ģ个
    -0.06
     Kn
    -0.06
    POSITIVE LOGITS
    ç¬¬åĽĽ
    0.08
    noz
    0.08
    é¼İé¼İ
    0.08
     ormai
    0.08
    çĤ¹å°ı
    0.08
    æ¯ĶæĪij们
    0.08
    缸åħ³éĹ®çŃĶ
    0.08
     Ùħزد
    0.07
    ZONE
    0.07
    ennie
    0.07
    Activations Density 0.004%

    No Known Activations