© 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. 39688
    Prev
    Next
    INDEX
    Explanations

    book reviews

    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
    ortal
    -0.08
    åĮ¹é©¬
    -0.07
     ():
    -0.06
    genic
    -0.06
    باÙĨ
    -0.06
     ìķĦëĭĪê³ł
    -0.06
    ãĤīãģĹãģı
    -0.06
    èĢĮç«ĭ
    -0.06
    çļĦå¸ĮæľĽ
    -0.06
    缸åħ³éĹ®çŃĶ
    -0.06
    POSITIVE LOGITS
     respectively
    0.12
    åIJİèĢħ
    0.11
     alike
    0.11
     serta
    0.10
     latter
    0.10
    ãģĦãģļãĤĮ
    0.09
    åĪĨåĪ«ä¸º
    0.08
    æ¾ľ
    0.08
    ä¸Ģä½ľ
    0.08
     sowie
    0.08
    Activations Density 1.014%

    No Known Activations