© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 700
    Prev
    Next
    INDEX
    Explanations

    access

    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
    تظ
    -0.25
    çī¹åĪ«å£°æĺİ
    -0.23
     difficoltÃł
    -0.21
    åŁºè°ĥ
    -0.20
     resultList
    -0.19
    nex
    -0.19
    ç½ijç«Ļåľ°åĽ¾
    -0.19
    èħł
    -0.19
    .RELATED
    -0.19
    èħĺ
    -0.19
    POSITIVE LOGITS
     freely
    0.35
    èĩªçĶ±
    0.33
     access
    0.33
    å¼ĢæĶ¾
    0.28
     unrestricted
    0.28
     possibility
    0.28
     freedom
    0.28
     доÑģÑĤÑĥп
    0.27
    ability
    0.27
    access
    0.26
    Activations Density 3.426%

    No Known Activations