© 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. 3062
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
     ($("#
    -0.21
    ARM
    -0.20
    /vendors
    -0.19
     accuses
    -0.19
    alborg
    -0.19
    åĨľåī¯
    -0.19
    Messenger
    -0.19
     pcm
    -0.18
    æĽ´å¤ļ精彩
    -0.18
    +"_
    -0.18
    POSITIVE LOGITS
     =>$
    0.27
    OLVE
    0.25
     (*((
    0.25
    syscall
    0.22
    ----</
    0.22
    SION
    0.21
    __,__
    0.21
        	č↵
    0.21
    naments
    0.21
    illos
    0.21
    Activations Density 0.012%

    No Known Activations