© 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. 3346
    Prev
    Next
    INDEX
    Explanations

    names and entities

    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
    :animated
    -0.23
    æį¢åı¥è¯Ŀ
    -0.22
     rencont
    -0.22
    é¦IJ
    -0.20
    SSFWorkbook
    -0.19
    xAB
    -0.19
     magg
    -0.19
    .Focused
    -0.18
    .Flags
    -0.18
    =*/
    -0.18
    POSITIVE LOGITS
    ожеÑĤ
    0.23
    emain
    0.21
     NavBar
    0.20
     fucks
    0.19
    apter
    0.19
    engeance
    0.19
    ereço
    0.19
    coon
    0.19
    phe
    0.19
    -aos
    0.19
    Activations Density 0.010%

    No Known Activations