© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 999
    Prev
    Next
    INDEX
    Explanations

    everyday activities

    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
    âĸ¹
    -0.23
     ;↵↵↵
    -0.22
    upported
    -0.20
     kijken
    -0.20
     aÄŁ
    -0.20
     }):
    -0.19
    髯
    -0.19
    setId
    -0.19
    neh
    -0.18
    çĸĥ
    -0.18
    POSITIVE LOGITS
     Åŀa
    0.22
     PaÅĦst
    0.21
     Ä°ns
    0.21
    ($('
    0.21
     RaycastHit
    0.20
    .Magenta
    0.20
     çeÅŁ
    0.19
    sandbox
    0.19
    åħ¶å®ĥéĹ®é¢ĺ
    0.19
    ç½ijåıĭè¯Ħ论
    0.19
    Activations Density 0.001%

    No Known Activations