© 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. 29559
    Prev
    Next
    INDEX
    Explanations

    utility and purpose

    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
    aum
    -0.06
    arma
    -0.06
    综åIJĪçĹĩ
    -0.06
    çĥŃéŨæłĩçŃ¾
    -0.06
    è¶
    -0.06
    åĬĽæ°Ķ
    -0.06
    urma
    -0.06
    综åIJĪåĪĨæŀIJ
    -0.06
    Keywords
    -0.06
    ube
    -0.06
    POSITIVE LOGITS
    å®ŀçĶ¨
    0.13
    å®ŀçĶ¨æĢ§
    0.12
    åĬŁèĥ½æĢ§
    0.11
    實çĶ¨
    0.10
    å®ŀçĶ¨çļĦ
    0.10
     practical
    0.10
    åĬŁèĥ½
    0.10
    -functional
    0.09
     functionality
    0.09
    Functional
    0.09
    Activations Density 0.244%

    No Known Activations