© 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. 1817
    Prev
    Next
    INDEX
    Explanations

    value of term

    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
    NgModule
    -0.28
    ç½ijé¦ĸ页
    -0.26
    foundland
    -0.26
    ðŁĮ°
    -0.25
     dealloc
    -0.23
    ,void
    -0.23
    SimpleName
    -0.23
    /grpc
    -0.23
    =\"/
    -0.23
    "<?
    -0.23
    POSITIVE LOGITS
     scaleX
    0.28
     disappe
    0.25
    åĮ
    0.24
     Erectile
    0.22
     irresist
    0.22
    çļĦçŃĶæ¡Ī
    0.21
     èĭ¥è¦ģ
    0.21
    feof
    0.21
    agascar
    0.21
     Hindered
    0.21
    Activations Density 0.636%

    No Known Activations