© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4377
    Prev
    Next
    INDEX
    Explanations

    see

    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
    Negative Logits
     SKF
    -0.27
     vegas
    -0.24
    æ¶ķ
    -0.23
     Finds
    -0.22
     giveaways
    -0.21
     prostit
    -0.20
     penet
    -0.20
    å¹´ä¸ĬåįĬå¹´
    -0.20
    ä¿Ł
    -0.20
     sclerosis
    -0.19
    POSITIVE LOGITS
    eggies
    0.31
    otime
    0.30
    odyn
    0.29
    eated
    0.28
    abez
    0.28
    odka
    0.27
    =\"/
    0.27
    ActionCreators
    0.26
    orthand
    0.26
    elsea
    0.26
    Activations Density 0.114%

    No Known Activations