© 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. 3020
    Prev
    Next
    INDEX
    Explanations

    code and data

    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
    ocache
    -0.24
     */č↵č↵č↵
    -0.21
     OnePlus
    -0.20
     UIBar
    -0.20
    _ioctl
    -0.19
    toJson
    -0.19
    -quote
    -0.19
    .ua
    -0.18
    /demo
    -0.18
     onchange
    -0.18
    POSITIVE LOGITS
    ActivityIndicator
    0.23
    âŁ¹
    0.23
     "','
    0.22
    anean
    0.22
    umbnail
    0.21
    ourke
    0.21
    zerbai
    0.21
    踽
    0.21
    BUFF
    0.21
    æĮ¹
    0.20
    Activations Density 0.052%

    No Known Activations