© 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. 276
    Prev
    Next
    INDEX
    Explanations

    buttons and links

    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
    åĭł
    -0.25
    ç½ijé¦ĸ页
    -0.25
     intptr
    -0.25
    usaha
    -0.25
     yay
    -0.25
    æ®ļ
    -0.24
     CAUSED
    -0.24
    alyzed
    -0.22
     Dems
    -0.21
    å¤įå·¥å¤į
    -0.21
    POSITIVE LOGITS
    #Region
    0.31
     semiclass
    0.24
    ombok
    0.24
    ."&
    0.24
     strugg
    0.23
    })();↵↵
    0.21
     ЧÑĤ
    0.21
    ñe
    0.21
    openh
    0.21
    ++;č↵č↵
    0.21
    Activations Density 4.813%

    No Known Activations