© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1500
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    EFAULT
    -0.24
     torino
    -0.21
    é²Ģ
    -0.21
    ='<?
    -0.20
    QRST
    -0.20
    .Raycast
    -0.20
    ngine
    -0.20
    énergie
    -0.20
    tabpanel
    -0.20
     CascadeType
    -0.20
    POSITIVE LOGITS
    (:,
    0.25
     (
    0.25
    (:,:,
    0.21
     TMPro
    0.20
     onPostExecute
    0.20
    NgModule
    0.19
    setImage
    0.19
    æ²ĥ
    0.19
    akedown
    0.19
     scop
    0.19
    Activations Density 0.175%

    No Known Activations