© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 902
    Prev
    Next
    INDEX
    Explanations

    2

    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
    çĹ¼
    -0.24
    å´Ľ
    -0.24
    åľ¨ä¼łå¥ĩ
    -0.23
    ãģıãģªãĤĬãģ¾ãģĹãģŁ
    -0.23
     disappe
    -0.21
    createQuery
    -0.21
    æķ´é½IJ
    -0.21
    irlines
    -0.20
    imagin
    -0.20
     sodom
    -0.19
    POSITIVE LOGITS
    ä¸Ĭä¸ĸ纪
    0.33
    GRADE
    0.24
     década
    0.22
    xFD
    0.21
    å½¹
    0.21
     scrimmage
    0.21
     decades
    0.20
    2
    0.20
    åħ¬åħĥ
    0.20
    CHandle
    0.20
    Activations Density 1.239%

    No Known Activations