© 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. 3089
    Prev
    Next
    INDEX
    Explanations

    indicates

    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
    .getElementsByName
    -0.21
    .Experimental
    -0.18
     spar
    -0.18
    OLVE
    -0.18
    æŃ
    -0.18
    aseline
    -0.18
    elden
    -0.17
    ï¿¡
    -0.17
    urry
    -0.17
    èĸ¤
    -0.17
    POSITIVE LOGITS
    表æĺİ
    0.73
    说æĺİ
    0.72
    說æĺİ
    0.52
    indic
    0.50
     indicates
    0.49
    è¯ģæĺİ
    0.48
     indicating
    0.47
     indicate
    0.45
    çĶ±æѤåı¯è§ģ
    0.44
     indication
    0.41
    Activations Density 0.487%

    No Known Activations