© 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. 3731
    Prev
    Next
    INDEX
    Explanations

    storing/hosting data

    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
     }):
    -0.23
    AtPath
    -0.22
    åĩºçİ°åľ¨
    -0.21
    /proto
    -0.21
    çķĻåľ¨
    -0.20
    ].'
    -0.20
    ;č↵č↵č↵č↵
    -0.20
    ä½ĵèĤ²åľ¨çº¿
    -0.20
    ."&
    -0.20
    微软éĽħé»ij
    -0.19
    POSITIVE LOGITS
    åŃĺæĶ¾
    0.39
    容纳
    0.39
    æݥ纳
    0.32
     storing
    0.30
    åĤ¨åŃĺ
    0.29
    åģľæĶ¾
    0.29
    åŃķèĤ²
    0.28
    æī¿è½½
    0.27
     storage
    0.26
     hosting
    0.26
    Activations Density 1.223%

    No Known Activations