© 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. 38
    Prev
    Next
    INDEX
    Explanations

    award

    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
    благо
    -0.26
     burge
    -0.25
    -scenes
    -0.24
    raq
    -0.24
     nors
    -0.24
    -exc
    -0.23
    -strokes
    -0.22
    entiful
    -0.22
    ANEL
    -0.21
    pson
    -0.21
    POSITIVE LOGITS
    å§ĭ建äºİ
    0.20
    _pb
    0.20
    											↵
    0.19
    æĹħ游度åģĩ
    0.19
    å¾ĴæŃ¥
    0.19
    award
    0.19
    æ¶Ķ
    0.19
    (javax
    0.18
    0.18
    getC
    0.18
    Activations Density 0.005%

    No Known Activations