© 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. 2241
    Prev
    Next
    INDEX
    Explanations

    says or reads

    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
    ystick
    -0.19
    úsqueda
    -0.19
    éments
    -0.19
    á¹ĵ
    -0.19
    ulk
    -0.19
    âce
    -0.19
    dsn
    -0.19
    èĴī
    -0.19
    ertiary
    -0.18
     Chapters
    -0.18
    POSITIVE LOGITS
    说éģĵ
    0.27
     reads
    0.26
    åĨĻéģĵ
    0.24
     Reads
    0.23
    æĿ¡è§Ħå®ļ
    0.22
     says
    0.21
    éĹ®éģĵ
    0.21
     stating
    0.21
     Says
    0.21
    æĢİä¹Ī说
    0.21
    Activations Density 0.220%

    No Known Activations