© 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. 3575
    Prev
    Next
    INDEX
    Explanations

    technical or code

    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
    ysqli
    -0.27
    ÙĪضÙĪع
    -0.22
    iffany
    -0.21
    }\.[
    -0.21
    ünün
    -0.20
     Mills
    -0.20
    )||(
    -0.20
    INNER
    -0.19
    :YES
    -0.19
    благо
    -0.19
    POSITIVE LOGITS
    çĽijåIJ¬é¡µéĿ¢
    0.21
     },{↵
    0.20
    éĺķ
    0.19
     didSelectRowAtIndexPath
    0.19
    .ToDateTime
    0.19
    entiful
    0.19
    åı¹äºĨåı£æ°Ķ
    0.18
    "]==
    0.18
     UIBar
    0.18
    wüns
    0.17
    Activations Density 0.002%

    No Known Activations