© 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. 38882
    Prev
    Next
    INDEX
    Explanations

    equal treatment or parity

    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
    hai
    -0.07
    enca
    -0.07
    èĩªèº«å»ºè®¾
    -0.07
    awan
    -0.07
    gau
    -0.07
    è¿Ĥ
    -0.07
    halen
    -0.07
    ä¸ŃåŃĹ
    -0.06
    çĶŁæ¶¯
    -0.06
    å°ļ
    -0.06
    POSITIVE LOGITS
    å¹³çŃī
    0.19
    å¹³çŃīçļĦ
    0.18
     equal
    0.15
     одина
    0.14
    equal
    0.14
     Equal
    0.14
     equality
    0.14
     equally
    0.14
     Equality
    0.13
    åIJĮçŃī
    0.13
    Activations Density 0.069%

    No Known Activations