© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 46
    Prev
    Next
    INDEX
    Explanations

    where

    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
     CORPOR
    -0.24
    ///č↵
    -0.23
    .Areas
    -0.21
    Couldn
    -0.21
    ä¸ī大éĺ¶æ®µ
    -0.20
     +#+
    -0.20
     pathMatch
    -0.19
     lawy
    -0.19
    levator
    -0.19
    çĹĦ
    -0.18
    POSITIVE LOGITS
    è¿ĻéĩĮçļĦ
    0.26
    顺
    0.24
    reeNode
    0.22
    áºł
    0.21
    бин
    0.20
    :Event
    0.20
    æīĢè°ĵ
    0.20
     here
    0.20
    ä¸Ģ个æĺ¯
    0.20
    /*↵
    0.20
    Activations Density 0.393%

    No Known Activations