© 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. 3227
    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
    æĶ¯çº¿ä»»åĬ¡
    -0.24
    á»ĩnh
    -0.21
    京
    -0.21
    ernational
    -0.20
    uos
    -0.20
     TYPO
    -0.20
    -deals
    -0.20
    nesty
    -0.19
    rray
    -0.19
     aj
    -0.19
    POSITIVE LOGITS
    intégr
    0.22
    çı§
    0.21
    >{@
    0.20
    ÑģÑĤолÑĮ
    0.20
    ãģĶ覧
    0.19
    失è°ĥ
    0.19
     då
    0.19
     gerekt
    0.19
    _nil
    0.18
    ger
    0.18
    Activations Density 0.000%

    No Known Activations