© 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. 14487
    Prev
    Next
    INDEX
    Explanations

    service discontinuation or announcement

    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
     primitive
    -0.07
     ensuing
    -0.07
     doubly
    -0.06
    第ä¸Ģ次
    -0.06
    åIJĪéĢĤ
    -0.06
    æĶ¶éŁ³
    -0.06
    æħ§èģªç½ij
    -0.06
    éħįèµĦ
    -0.06
     p
    -0.06
     g
    -0.06
    POSITIVE LOGITS
    å®ĺæĸ¹
    0.10
     discontinued
    0.10
     announced
    0.10
    Official
    0.10
     official
    0.10
     officially
    0.10
    official
    0.09
    æĸĩåįİ
    0.09
    åħ¶æŀĹ
    0.09
     оÑĦиÑĨиалÑĮнÑĭй
    0.08
    Activations Density 0.469%

    No Known Activations