© 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. 1206
    Prev
    Next
    INDEX
    Explanations

    feelings or emotions

    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
    RTOS
    -0.24
    :[[
    -0.23
     bigot
    -0.22
    documento
    -0.22
     strSQL
    -0.22
    /inet
    -0.22
    _documento
    -0.21
    /backend
    -0.21
     saddened
    -0.21
    precation
    -0.21
    POSITIVE LOGITS
     Self
    0.28
     feelings
    0.27
     self
    0.26
    èĩªæĪij
    0.25
     lowes
    0.25
     inner
    0.25
     experiences
    0.25
    Self
    0.24
    isLoggedIn
    0.23
    åīĸæŀIJ
    0.23
    Activations Density 4.198%

    No Known Activations