© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3990
    Prev
    Next
    INDEX
    Explanations

    The

    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
    ãĥµ
    -0.23
     Stuff
    -0.22
    rances
    -0.21
    æ½ĭ
    -0.20
    Stuff
    -0.19
    .FindGameObjectWithTag
    -0.19
     Sach
    -0.18
    Latch
    -0.17
    thal
    -0.17
    ffect
    -0.17
    POSITIVE LOGITS
     authors
    0.22
    ummings
    0.21
    oya
    0.21
    ä½ľèĢħ
    0.21
    erland
    0.21
    :".$
    0.19
     author
    0.19
    è°ĭ
    0.19
    '].$
    0.19
    astered
    0.19
    Activations Density 0.139%

    No Known Activations