© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3956
    Prev
    Next
    INDEX
    Explanations

    U

    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
    ?('
    -0.20
    @show
    -0.20
    CJK
    -0.20
    æĹ»
    -0.20
     "'.
    -0.19
    &display
    -0.19
    éĩı
    -0.19
    	fflush
    -0.19
     createStackNavigator
    -0.19
    âĸ·
    -0.19
    POSITIVE LOGITS
    /stretch
    0.23
    -describedby
    0.22
    wers
    0.20
     philippines
    0.19
    orc
    0.19
     Helmet
    0.18
    ä»ĩ
    0.18
    contra
    0.18
    izabeth
    0.18
    unate
    0.18
    Activations Density 0.011%

    No Known Activations