© 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. 3474
    Prev
    Next
    INDEX
    Explanations

    code and file paths

    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
    mouseup
    -0.29
    -prepend
    -0.27
    apesh
    -0.25
    家éĥ½çŁ¥éģĵ
    -0.24
    ?>>
    -0.23
    ',//
    -0.22
    ?>/
    -0.22
    /Branch
    -0.22
    )item
    -0.22
    mouseenter
    -0.22
    POSITIVE LOGITS
    åħ¨æĹ¥
    0.21
    .Locale
    0.21
     pav
    0.20
     redistribute
    0.20
     Satoshi
    0.19
     '{{
    0.19
     FXMLLoader
    0.18
     Fully
    0.18
     Georges
    0.18
    aud
    0.18
    Activations Density 0.007%

    No Known Activations