© 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. 2690
    Prev
    Next
    INDEX
    Explanations

    legal orders and documents

    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
    .dataTables
    -0.23
    Nguá»ĵn
    -0.22
    nofollow
    -0.22
     (){
    -0.21
    oston
    -0.20
    åŁŃ
    -0.20
     ragazzo
    -0.20
    trib
    -0.20
    =""/>↵
    -0.19
    éĻ¤
    -0.19
    POSITIVE LOGITS
    åħ¹
    0.23
     (!((
    0.22
    åľ¨çݩ家ä¸Ń
    0.20
    ãĥµ
    0.20
    à¸ŀฤ
    0.20
    /***/
    0.19
     AppRoutingModule
    0.19
    REA
    0.19
     believable
    0.19
    æĤļ
    0.19
    Activations Density 0.123%

    No Known Activations