© 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. 3901
    Prev
    Next
    INDEX
    Explanations

    clear

    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
    ÑģÑĤолÑĮ
    -0.24
    -REAL
    -0.22
    EMS
    -0.21
    еÑģÑĤеÑģÑĤв
    -0.21
    IRQ
    -0.21
    ESCO
    -0.21
    ierge
    -0.20
    andalone
    -0.20
    ENTIC
    -0.20
    memberof
    -0.19
    POSITIVE LOGITS
    æ¸ħæĻ°
    0.27
    :both
    0.26
    orias
    0.25
    æ¸ħæ¥ļ
    0.24
    çľĭåĩº
    0.23
    -cut
    0.23
    _codigo
    0.23
    æĺİæĺ¾çļĦ
    0.23
     clear
    0.23
    FormsModule
    0.23
    Activations Density 0.121%

    No Known Activations