© 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. 3466
    Prev
    Next
    INDEX
    Explanations

    Our

    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
    Not in Any Lists

    No Comments

    Negative Logits
    对çħ§æ£ĢæŁ¥
    -0.30
    -END
    -0.27
    æĴº
    -0.26
    æĤ»
    -0.24
    ï¿¡
    -0.24
     ámb
    -0.23
    ︱
    -0.23
    âĸİ
    -0.23
    еÑģÑĤеÑģÑĤв
    -0.22
    rd
    -0.22
    POSITIVE LOGITS
    ivr
    0.34
     disastr
    0.34
    Ỹ
    0.31
    Ũ
    0.31
    gages
    0.31
    zzle
    0.31
    Äī
    0.30
    gnore
    0.30
     sodom
    0.30
    dle
    0.30
    Activations Density 0.089%

    No Known Activations