© 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. 14773
    Prev
    Next
    INDEX
    Explanations

    inverse relationship, rates, coefficients, mapping

    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
    pty
    -0.08
    è¿ĶåĽŀåĪĹ表
    -0.08
     esac
    -0.08
    éĶ¦æłĩ
    -0.07
    ewa
    -0.07
    ÑĤÑĢа
    -0.07
    çĽ¸ä¿¡åľ¨
    -0.07
    Locker
    -0.07
    opl
    -0.07
    åIJ¸å¼ķ人çļĦ
    -0.07
    POSITIVE LOGITS
     reciprocal
    0.09
    atto
    0.08
     inverse
    0.07
     relationship
    0.07
    ä¹ĭéĹ´çļĦåħ³ç³»
    0.07
    akai
    0.07
    sett
    0.07
    æĽ´çĶŁ
    0.07
    Inverse
    0.07
     recip
    0.07
    Activations Density 0.001%

    No Known Activations