© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3422
    Prev
    Next
    INDEX
    Explanations

    technical or scientific text

    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
    Ĥ¬
    -0.22
    æĢ§è´¨
    -0.20
     nature
    -0.20
    strpos
    -0.19
     cr
    -0.19
    åıĸåĨ³
    -0.19
    łģ
    -0.19
    éĢ¸
    -0.19
    æķŀ
    -0.19
     armed
    -0.19
    POSITIVE LOGITS
     tph
    0.24
     {{--<
    0.24
     lowes
    0.23
     ÃĶ
    0.23
    ONEY
    0.22
    ?url
    0.22
    =";↵
    0.21
    iks
    0.21
     squeez
    0.21
    izzie
    0.20
    Activations Density 0.001%

    No Known Activations