© 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. 2411
    Prev
    Next
    INDEX
    Explanations

    code and programming

    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
    ,},↵
    -0.24
    exampleModal
    -0.24
    	throws
    -0.22
    iad
    -0.21
    OffsetTable
    -0.21
    stitial
    -0.21
     sluts
    -0.20
     onCancelled
    -0.20
    indsay
    -0.20
    讫
    -0.20
    POSITIVE LOGITS
     Jam
    0.23
    çݩ家æĿ¥è¯´
    0.20
    å¾Īå¤ļçݩ家
    0.20
    游æĪıéĩĮçļĦ
    0.19
    AREN
    0.19
    è¿ĩéĶĻ
    0.19
    aren
    0.18
    å¦Ĥæŀľçݩ家
    0.18
     gum
    0.18
    ë´¤
    0.18
    Activations Density 0.052%

    No Known Activations