© 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. 3955
    Prev
    Next
    INDEX
    Explanations

    programming terms

    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
    ////↵
    -0.20
    eliac
    -0.19
    (){}↵
    -0.19
    幡
    -0.19
    osci
    -0.18
    _THAT
    -0.18
    UIImageView
    -0.17
    åħ¨æĹ¥
    -0.17
    semble
    -0.17
    é¾ĩ
    -0.17
    POSITIVE LOGITS
     IU
    0.23
    vrolet
    0.21
    ');?>↵
    0.21
     ValueEventListener
    0.21
    INS
    0.21
    erti
    0.20
     OnCollision
    0.20
    occo
    0.20
    .jsoup
    0.20
    .textLabel
    0.19
    Activations Density 0.001%

    No Known Activations