© 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. 17209
    Prev
    Next
    INDEX
    Explanations

    fractional splines

    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
    bah
    -0.08
     merito
    -0.07
    è±ģ
    -0.07
    éĤ£æŶçļĦ
    -0.07
     numbering
    -0.07
    clare
    -0.07
     mote
    -0.07
    ÙĪØ·
    -0.07
     maté
    -0.07
    -*-
    -0.07
    POSITIVE LOGITS
     components
    0.09
     Components
    0.09
    -components
    0.09
    Components
    0.09
    éĥ¨åĪĨç»ĦæĪIJ
    0.08
    -component
    0.08
    éĥ¨åĪĨçļĦ
    0.08
     orthogonal
    0.08
     portion
    0.08
     componenti
    0.08
    Activations Density 0.003%

    No Known Activations