© 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. 444
    Prev
    Next
    INDEX
    Explanations

    I is

    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
    .gstatic
    -0.22
     /************************************************************************
    -0.21
     çĶŁåij½åij¨æľŁ
    -0.20
     âĺĨ
    -0.20
     ún
    -0.20
     (~(
    -0.19
     èĩªåĬ¨çĶŁæĪIJ
    -0.19
    ä¹Łåı¯èĥ½
    -0.19
    INCLUDED
    -0.19
    longleftrightarrow
    -0.19
    POSITIVE LOGITS
    éľĢè¦ģ
    0.85
     need
    0.75
     needs
    0.70
     needed
    0.64
     needing
    0.64
    need
    0.59
    éľĢæ±Ĥ
    0.59
    éľĢè¦ģçĶ¨
    0.59
     Need
    0.57
     cần
    0.56
    Activations Density 6.193%

    No Known Activations