© 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. 238
    Prev
    Next
    INDEX
    Explanations

    possibility

    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
     EITHER
    -0.29
    è¦ģä¹Ī
    -0.27
    ãģ¨ãģ«ãģĭãģı
    -0.25
    rô
    -0.21
    média
    -0.20
    posição
    -0.20
     threadIdx
    -0.20
     citiz
    -0.20
    edad
    -0.20
     однако
    -0.19
    POSITIVE LOGITS
     maybe
    0.34
     perhaps
    0.33
     possibly
    0.30
    çĶļèĩ³
    0.29
    maybe
    0.27
     even
    0.27
     probably
    0.27
    [".
    0.26
    ä¸įä¸Ģå®ļ
    0.26
    æľªå¿ħ
    0.26
    Activations Density 3.172%

    No Known Activations