© 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. 2172
    Prev
    Next
    INDEX
    Explanations

    plenty

    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
    lke
    -0.25
     kto
    -0.22
    åıĪè¦ģ
    -0.22
    ä¹Łåıªèĥ½
    -0.22
    alleries
    -0.22
    .dateFormat
    -0.21
    ä¸įåı¯æĪĸ
    -0.20
    Ľå»º
    -0.20
    owntown
    -0.20
    actus
    -0.20
    POSITIVE LOGITS
     plenty
    0.37
    足以
    0.36
    å®Įåħ¨åı¯ä»¥
    0.33
     sufficient
    0.32
     Plenty
    0.32
    åħĭæľį
    0.32
    å¾Īå¿«
    0.30
    足
    0.29
    å¾Īå¿«å°±
    0.28
    è¶³å¤Ł
    0.28
    Activations Density 0.520%

    No Known Activations