© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2588
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     (*((
    -0.22
    #ab
    -0.21
    apons
    -0.21
    rog
    -0.20
    )new
    -0.20
    (++
    -0.20
    tti
    -0.20
    auważ
    -0.19
    åĹIJ
    -0.19
    (IM
    -0.19
    POSITIVE LOGITS
    æı¶
    0.23
    HorizontalAlignment
    0.21
    clusão
    0.21
    .circular
    0.20
    :relative
    0.20
    elay
    0.19
    innitus
    0.19
    æŃ£å¸¸ä½¿çĶ¨
    0.19
     Dota
    0.19
    åĢŁ
    0.19
    Activations Density 0.000%

    No Known Activations