© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1301
    Prev
    Next
    INDEX
    Explanations

    legal document identifiers

    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
    avanaugh
    -0.24
    @testable
    -0.20
    orsche
    -0.19
    MOOTH
    -0.19
    å¢ŀå¹ħ
    -0.19
    缸åħ³æĸ°éĹ»
    -0.19
    NgModule
    -0.19
    idelberg
    -0.19
    æ¯ıæĹ¥ç»ıæµİ
    -0.18
    çĮ¾
    -0.18
    POSITIVE LOGITS
    }elseif
    0.31
    ãĥµ
    0.29
    áºĴ
    0.22
    toggleClass
    0.21
    -scenes
    0.21
     Dems
    0.20
    ="__
    0.20
    polator
    0.20
    etchup
    0.20
    -scrollbar
    0.20
    Activations Density 0.745%

    No Known Activations