© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1812
    Prev
    Next
    INDEX
    Explanations

    both

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    @brief
    -0.25
    addtogroup
    -0.23
    ximity
    -0.21
    تظ
    -0.20
    æĪĸèĢħåħ¶ä»ĸ
    -0.20
    جاد
    -0.19
    ointed
    -0.19
     именно
    -0.18
     TMPro
    -0.17
    Ùģار
    -0.17
    POSITIVE LOGITS
     sexes
    0.40
     sides
    0.28
     genders
    0.25
    Hôtel
    0.24
    ç«ĻçĿĢ
    0.24
    éŃĶæ³ķå¸ĪåĴĮ
    0.24
    asurer
    0.23
     halves
    0.23
    uforia
    0.23
    ;',↵
    0.23
    Activations Density 0.902%

    No Known Activations