© 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. 491
    Prev
    Next
    INDEX
    Explanations

    references and notes

    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
    JKLMNOP
    -0.22
    HeaderCode
    -0.21
    æį
    -0.20
    "<?
    -0.20
    :"",
    -0.20
    ildo
    -0.19
    Editar
    -0.18
    .Tags
    -0.18
    swire
    -0.18
    -wsj
    -0.18
    POSITIVE LOGITS
     note
    0.23
    åıĤèĢĥ
    0.23
     refer
    0.23
     references
    0.23
    åıĤ
    0.21
     reference
    0.20
     refers
    0.20
     Note
    0.20
     See
    0.19
     Refer
    0.19
    Activations Density 0.269%

    No Known Activations