© 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. 3366
    Prev
    Next
    INDEX
    Explanations

    *

    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
    Ø£ÙģÙĥار
    -0.25
     kull
    -0.25
    ].'
    -0.25
    )||(
    -0.25
    lÃł
    -0.24
    ilmington
    -0.24
    ][]
    -0.24
     practition
    -0.23
    .openConnection
    -0.23
    -Za
    -0.22
    POSITIVE LOGITS
     çĶŁåij½åij¨æľŁåĩ½æķ°
    0.23
    mouseup
    0.23
    [
    0.21
    mousedown
    0.20
    çļĦä¸Ģç§į
    0.20
    ä»ĸåıĪ
    0.19
    uckland
    0.19
    ä¹ĥ
    0.19
     springfox
    0.18
    wrapper
    0.18
    Activations Density 0.030%

    No Known Activations