© 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. 3522
    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
    som
    -0.23
    dit
    -0.21
    .esp
    -0.21
    ðŁļ©
    -0.20
    dex
    -0.20
     beÄŁen
    -0.20
    ":""
    -0.20
    housing
    -0.19
    ntp
    -0.19
    forgettable
    -0.19
    POSITIVE LOGITS
     molec
    0.21
    Ymd
    0.20
    çķ¦
    0.20
    èĭ¥æľī
    0.19
    äºĮæľŁ
    0.18
    åį§
    0.18
    å¡
    0.18
    ecided
    0.18
    Cette
    0.18
    .Include
    0.18
    Activations Density 0.000%

    No Known Activations