© 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. 2646
    Prev
    Next
    INDEX
    Explanations

    height or size

    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
    /MPL
    -0.29
    stery
    -0.27
    oader
    -0.27
    -Cs
    -0.26
     earthqu
    -0.25
    !!");↵
    -0.24
    .ToShort
    -0.24
     ×Ķ×ķ×ĵ
    -0.23
    #ab
    -0.23
    EdgeInsets
    -0.23
    POSITIVE LOGITS
     tallest
    0.20
     exp
    0.20
    mouseup
    0.19
    è¾ķ
    0.19
     tall
    0.19
     strugg
    0.19
    æĴŃ
    0.18
    é»Ħéĩij
    0.18
    Ŀ
    0.18
    _UNLOCK
    0.18
    Activations Density 0.018%

    No Known Activations