© 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. 42317
    Prev
    Next
    INDEX
    Explanations

    math and decimals

    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
    ewise
    -0.07
    REFERENCES
    -0.07
     Anc
    -0.06
    öch
    -0.06
     CONTRIBUT
    -0.06
    ä½ķç§į
    -0.06
    yel
    -0.06
    çļĦæĸ°çĶŁ
    -0.06
    è½»
    -0.06
    å°ĨæѤ
    -0.06
    POSITIVE LOGITS
    åĽłæķ°
    0.11
     decimals
    0.09
     маÑĤем
    0.09
     algebra
    0.09
     decimal
    0.09
     math
    0.09
    å°ıæķ°
    0.09
    æķ°åѦ
    0.09
    Decimal
    0.09
    åĢįæķ°
    0.08
    Activations Density 0.021%

    No Known Activations