© 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. 3066
    Prev
    Next
    INDEX
    Explanations

    software components

    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
    çħŀ
    -0.21
     hinter
    -0.20
    ui
    -0.20
     them
    -0.19
    istingu
    -0.19
    oner
    -0.19
     binary
    -0.18
    /apt
    -0.18
    俨
    -0.18
    åij¼åĶ¤
    -0.18
    POSITIVE LOGITS
    ovah
    0.25
    azı
    0.23
    ilmiÅŁ
    0.23
    vider
    0.22
    ROID
    0.21
    AppComponent
    0.21
    æĩij
    0.21
    WiÄĻcej
    0.20
     WATCH
    0.20
     AssemblyVersion
    0.20
    Activations Density 0.001%

    No Known Activations