© 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. 953
    Prev
    Next
    INDEX
    Explanations

    technical domains

    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
    verständlich
    -0.27
    ialized
    -0.25
    ;o
    -0.24
    âļĹ
    -0.24
    åħ¨åĬĽä»¥
    -0.23
    @student
    -0.23
    .ManyToMany
    -0.23
    âĮĤ
    -0.23
    ä½ĵèĤ²æĬķ注
    -0.23
    ðŁĵIJ
    -0.22
    POSITIVE LOGITS
    ®
    0.36
    .BLL
    0.25
    .org
    0.25
    ®,
    0.24
    .com
    0.23
    's
    0.23
     handguns
    0.22
     ®
    0.22
    -
    0.21
     nonatomic
    0.21
    Activations Density 6.000%

    No Known Activations