© 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. 1833
    Prev
    Next
    INDEX
    Explanations

    software license

    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
    variably
    -0.27
    åĺīå¹´
    -0.22
    .scalajs
    -0.21
    éĶĥ
    -0.21
    å¸Ĥå§Ķ常å§Ķ
    -0.20
    péri
    -0.20
    actly
    -0.20
     the
    -0.20
    å±¾
    -0.19
     @$_
    -0.19
    POSITIVE LOGITS
     portion
    0.35
    iest
    0.27
    éĥ¨åĪĨ
    0.24
    portion
    0.24
    frage
    0.23
     situation
    0.23
     idea
    0.23
     ));č↵
    0.22
    ses
    0.22
    çİij
    0.22
    Activations Density 9.192%

    No Known Activations