© 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. 2622
    Prev
    Next
    INDEX
    Explanations

    specific terms

    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
    arendra
    -0.23
    ".$_
    -0.23
    ,GL
    -0.22
     ActionTypes
    -0.21
    .JScrollPane
    -0.20
    ︰
    -0.20
    .MILLISECONDS
    -0.20
    SEX
    -0.19
    æ·ı
    -0.19
    âĺŁ
    -0.19
    POSITIVE LOGITS
    rchive
    0.22
    Occurred
    0.21
    ocator
    0.20
     kennenlernen
    0.20
    egot
    0.19
     Hermes
    0.19
    .Sockets
    0.19
    aveled
    0.19
    nces
    0.19
    æµģæ°´
    0.19
    Activations Density 0.001%

    No Known Activations