© 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. 3586
    Prev
    Next
    INDEX
    Explanations

    unique entities name

    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
    >Password
    -0.22
    uslim
    -0.22
    erala
    -0.22
    mploy
    -0.20
     konk
    -0.20
     FixedUpdate
    -0.20
    ächst
    -0.20
    illator
    -0.20
    incare
    -0.19
    nces
    -0.19
    POSITIVE LOGITS
     '".$_
    0.23
    ;o
    0.21
    ^K
    0.21
    ,eg
    0.20
    uctor
    0.20
    è¹ĩ
    0.20
    ä¼ī
    0.19
    íĶĦë¡ľê·¸
    0.19
     hubby
    0.19
    .writeHead
    0.19
    Activations Density 0.003%

    No Known Activations