© 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. 1006
    Prev
    Next
    INDEX
    Explanations

    something, anything, nothing

    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
    IDEOS
    -0.25
    forcements
    -0.24
    èħ§
    -0.23
    tÃł
    -0.22
    ornment
    -0.21
     hadde
    -0.21
     italiani
    -0.21
    odyn
    -0.21
     gode
    -0.21
     mies
    -0.21
    POSITIVE LOGITS
     happening
    0.41
     happen
    0.34
     happens
    0.33
     else
    0.32
     done
    0.31
     happened
    0.31
     Happ
    0.31
    åıijçĶŁ
    0.30
     wrong
    0.29
     accomplished
    0.27
    Activations Density 1.498%

    No Known Activations