© 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. 40293
    Prev
    Next
    INDEX
    Explanations

    neutral and ionic species

    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
     Convenient
    -0.08
    indr
    -0.07
    äºīä¼ĺ
    -0.07
     postId
    -0.07
    projectId
    -0.07
    inds
    -0.07
     mòn
    -0.07
     кÑĢово
    -0.07
    槽
    -0.07
     Bref
    -0.07
    POSITIVE LOGITS
    æĪĸå°ij
    0.08
    ä¸ŃæĢ§
    0.08
    ä»·
    0.08
    亲
    0.07
    价为
    0.07
     neutral
    0.07
    neutral
    0.06
    ä»·çļĦ
    0.06
     entity
    0.06
    å®ŀçļĦ
    0.06
    Activations Density 0.011%

    No Known Activations