© 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. 3822
    Prev
    Next
    INDEX
    Explanations

    1

    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
    rippling
    -0.23
    postalcode
    -0.21
     `,↵
    -0.21
    çĸĸ
    -0.20
    .Tags
    -0.20
    '])?
    -0.20
    mouseenter
    -0.19
     reass
    -0.19
    p
    -0.19
    mouseleave
    -0.18
    POSITIVE LOGITS
    ðŁĵIJ
    0.22
    ADX
    0.22
    éĿŀ常å¤ļçļĦ
    0.22
    âļĹ
    0.21
     Decompiled
    0.21
    èįı
    0.21
    éķ
    0.21
    comings
    0.21
    ABCDEFG
    0.21
    }č↵č↵č↵č↵
    0.20
    Activations Density 0.049%

    No Known Activations