© 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. 2648
    Prev
    Next
    INDEX
    Explanations

    technical web content Q&A

    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
    [url
    -0.21
    roupon
    -0.21
    umpt
    -0.20
    amy
    -0.19
    USART
    -0.19
     Minor
    -0.19
    *Math
    -0.19
    ÅŃ
    -0.18
    -required
    -0.18
    Lng
    -0.18
    POSITIVE LOGITS
    rok
    0.19
    -svg
    0.19
    expects
    0.19
     Dems
    0.19
    orama
    0.19
    LATED
    0.19
     horny
    0.19
     jihadists
    0.19
    SCALL
    0.18
    )const
    0.18
    Activations Density 0.001%

    No Known Activations