© 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. 2720
    Prev
    Next
    INDEX
    Explanations

    Q and 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
    ramework
    -0.20
    éªĭ
    -0.20
    ÅĤoży
    -0.20
    çī¹åĪ«å£°æĺİ
    -0.20
    erÃł
    -0.19
    orgeous
    -0.19
     eius
    -0.18
    ounters
    -0.18
    imately
    -0.18
     ph
    -0.18
    POSITIVE LOGITS
    crast
    0.21
    æİ°
    0.21
     ApplicationDbContext
    0.20
    ëķħ
    0.19
    uforia
    0.18
    innacle
    0.18
     pacman
    0.17
    hurst
    0.17
    ி
    0.17
    {Name
    0.17
    Activations Density 0.001%

    No Known Activations