© 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. 3244
    Prev
    Next
    INDEX
    Explanations

    unusual characters

    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
    êµ°
    -0.19
    çĶ¸
    -0.19
    !important
    -0.19
    bservable
    -0.18
     arg
    -0.18
     zes
    -0.18
    (sec
    -0.18
    .arg
    -0.18
    elsif
    -0.18
    exao
    -0.18
    POSITIVE LOGITS
    åİŁæĸĩåľ°åĿĢ
    0.22
    /octet
    0.22
    @student
    0.21
    etre
    0.19
    éħŀ
    0.19
    UGIN
    0.18
    bsites
    0.18
    herits
    0.18
    ahir
    0.18
    ìĿ¸íĦ°
    0.18
    Activations Density 0.001%

    No Known Activations