© 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. 3656
    Prev
    Next
    INDEX
    Explanations

    code and programming

    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
    åij¸
    -0.20
    sembly
    -0.19
     valu
    -0.19
     responseBody
    -0.19
    åı¥è¯Ŀ
    -0.19
     numberWith
    -0.18
    isses
    -0.18
    è¿Ļ个éĹ®é¢ĺ
    -0.18
    åĩ¤åĩ°ç½ij
    -0.18
    两端
    -0.17
    POSITIVE LOGITS
    á½ģ
    0.22
    >tag
    0.22
    {-#
    0.20
    DL
    0.20
    ?("
    0.20
     skulle
    0.20
    volução
    0.20
    >('
    0.20
    uil
    0.20
     AngularFire
    0.18
    Activations Density 0.002%

    No Known Activations