© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3152
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    èįij
    -0.24
    linkplain
    -0.22
    "bytes
    -0.21
     *</
    -0.21
    éĶµ
    -0.21
    reactstrap
    -0.21
    æŁ¥çľĭ详æĥħ
    -0.20
    kiego
    -0.20
    åij¸
    -0.19
    tract
    -0.19
    POSITIVE LOGITS
    å·®çĤ¹
    0.21
    å¦Ħ
    0.20
    jury
    0.20
    å¹´ä¹ĭä¹ħ
    0.19
    osemite
    0.18
     Jury
    0.18
    çŀ¬éĹ´
    0.17
    à¹Ĥà¸Ł
    0.17
    @g
    0.17
    æİ¥
    0.17
    Activations Density 0.000%

    No Known Activations