© 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. 1760
    Prev
    Next
    INDEX
    Explanations

    statistical factors

    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
     misd
    -0.24
    ofday
    -0.24
     assh
    -0.23
    大纲
    -0.23
     ""},↵
    -0.22
     dicks
    -0.21
    :disable
    -0.21
     swinger
    -0.21
     asshole
    -0.20
    åı¯æĥ³
    -0.20
    POSITIVE LOGITS
     variables
    0.29
     factors
    0.28
    åıĺéĩı
    0.27
    åĽłç´ł
    0.27
    åĽłåŃIJ
    0.24
     factor
    0.24
     independently
    0.23
    åħ¨åĬĽä»¥
    0.23
     independent
    0.22
    æĮĩæłĩ
    0.22
    Activations Density 2.090%

    No Known Activations