© 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. 1023
    Prev
    Next
    INDEX
    Explanations

    court case 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
    åĬŀåħ¬åİħ
    -0.22
    æĮ¹
    -0.22
    åIJįåĪĹåīį
    -0.21
    æļĮ
    -0.21
    æŃ¤æ¬¡æ´»åĬ¨
    -0.21
    ified
    -0.20
    quartered
    -0.20
    @Id
    -0.20
     Baghd
    -0.20
     UITableViewDataSource
    -0.19
    POSITIVE LOGITS
    deaux
    0.22
    ocht
    0.22
    Ø£ÙĪض
    0.21
    akra
    0.21
    /AFP
    0.19
    ter
    0.19
    acman
    0.18
    åŃĹ第
    0.18
    _builtin
    0.18
    èĮ¹
    0.18
    Activations Density 1.371%

    No Known Activations