© 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. 2556
    Prev
    Next
    INDEX
    Explanations

    programming/code 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
    .scalablytyped
    -0.26
    NavController
    -0.24
    incinnati
    -0.23
     Heard
    -0.22
    ummings
    -0.21
    .$.
    -0.21
    repid
    -0.21
    º
    -0.20
     Xperia
    -0.20
    tram
    -0.20
    POSITIVE LOGITS
    _HINT
    0.23
     AngularFire
    0.20
    afür
    0.19
    tener
    0.19
    .cuda
    0.18
    etat
    0.18
     hint
    0.18
     УкÑĢа
    0.17
    éĢĶå¾Ħ
    0.17
    .hasMore
    0.17
    Activations Density 0.001%

    No Known Activations