© 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. 2817
    Prev
    Next
    INDEX
    Explanations

    which

    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
    1
    -0.20
     hl
    -0.20
     different
    -0.20
    ä¿Ŀ
    -0.19
    re
    -0.19
    8
    -0.19
    ç»ı
    -0.19
    9
    -0.19
    7
    -0.19
    2
    -0.19
    POSITIVE LOGITS
     Ones
    0.26
     actionTypes
    0.26
    ersed
    0.26
    ç¾İåªĴ
    0.25
    grily
    0.25
    elerik
    0.25
    åı¹äºĨ
    0.25
    entiful
    0.24
    curacy
    0.24
     ones
    0.24
    Activations Density 0.022%

    No Known Activations