© 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. 615
    Prev
    Next
    INDEX
    Explanations

    numerical order

    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
    .SingleOrDefault
    -0.25
    ç¾İåªĴ
    -0.24
    åħ«åįģ
    -0.24
    ãī
    -0.23
    æ°°
    -0.22
    äºĶçĻ¾
    -0.21
    .showError
    -0.20
    ISMATCH
    -0.20
    ä¸ĥåįģ
    -0.20
    WXYZ
    -0.20
    POSITIVE LOGITS
    ¡´
    0.25
     two
    0.25
    agascar
    0.24
    两个维æĬ¤
    0.23
    .jface
    0.22
    å¥ĸåѦ
    0.22
    two
    0.22
     second
    0.22
    bred
    0.22
    éĩĩçŁ¿çŃī
    0.21
    Activations Density 1.441%

    No Known Activations