© 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. 1215
    Prev
    Next
    INDEX
    Explanations

    actions and states

    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
     pestic
    -0.20
     '../../../../../
    -0.19
    räg
    -0.19
     AudioSource
    -0.19
    åĤ¬
    -0.19
     {\↵
    -0.19
     Método
    -0.19
    .descripcion
    -0.18
    noch
    -0.18
    azers
    -0.18
    POSITIVE LOGITS
    è¶Ķ
    0.28
    ,Yes
    0.24
    ï¼ģ",
    0.24
    ")));
    0.23
     beÄŁen
    0.23
    ︱
    0.23
    é¾ĥ
    0.23
    OLUMN
    0.22
    åIJįåĪĹåīį
    0.22
    pherd
    0.22
    Activations Density 4.759%

    No Known Activations