© 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. 3729
    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
     órgão
    -0.21
     AppBundle
    -0.21
    pesan
    -0.19
     اÙĦÙĤادÙħ
    -0.19
     likeness
    -0.19
    çļĦä¿¡å¿ĥ
    -0.18
    nonnull
    -0.18
    弯
    -0.18
    è¡·å¿ĥ
    -0.18
    æĶ¶åĪ°äºĨ
    -0.17
    POSITIVE LOGITS
    :';↵
    0.29
    /Dk
    0.28
    éĶĺ
    0.28
    ðŁĺī
    0.27
    ecer
    0.24
    æ·ı
    0.24
    ivr
    0.24
    éªī
    0.24
    ))==
    0.23
    ','');↵
    0.23
    Activations Density 0.000%

    No Known Activations