© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2437
    Prev
    Next
    INDEX
    Explanations

    HTML paragraph tag

    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
     membr
    -0.21
    å¾Īå¤ļçݩ家
    -0.21
    åłī
    -0.20
    -Assad
    -0.20
    .appspot
    -0.20
    èĭ¥æĤ¨
    -0.20
    berra
    -0.20
    家éĥ½çŁ¥éģĵ
    -0.19
    ÑĥниÑĨип
    -0.19
    /fw
    -0.19
    POSITIVE LOGITS
     Blasio
    0.26
    олÑĮз
    0.24
    .Comparator
    0.23
    íĤ´
    0.20
    ÑĪиб
    0.19
    (CharSequence
    0.19
    ANTA
    0.19
     FixedUpdate
    0.18
    .gstatic
    0.18
    еÑģ
    0.18
    Activations Density 0.010%

    No Known Activations