© 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. 3271
    Prev
    Next
    INDEX
    Explanations

    feeling

    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
    ornings
    -0.23
    unken
    -0.22
    chedulers
    -0.20
    apesh
    -0.20
     InitializeComponent
    -0.20
    اÙĦأر
    -0.20
    å»ĭ
    -0.20
    è§ģè¯Ĩ
    -0.20
    إز
    -0.20
    以人æ°ij为
    -0.20
    POSITIVE LOGITS
     feel
    0.32
    使人
    0.31
     feeling
    0.31
     felt
    0.29
     feels
    0.29
    ç»Ļ人
    0.29
    ç»Ļ人ä¸Ģç§į
    0.29
     viewer
    0.26
    让人
    0.26
     viewers
    0.25
    Activations Density 0.524%

    No Known Activations