© 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. 2026
    Prev
    Next
    INDEX
    Explanations

    citations

    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
    .handleSubmit
    -0.23
    utow
    -0.22
    icester
    -0.22
    .radioButton
    -0.21
    indered
    -0.20
    readystatechange
    -0.20
    ISTS
    -0.19
    aveled
    -0.19
    ElementException
    -0.19
    utdown
    -0.18
    POSITIVE LOGITS
     bénéficie
    0.21
    smouth
    0.21
    retweeted
    0.20
    .timedelta
    0.20
    ksztaÅĤ
    0.20
    est
    0.19
    RouterModule
    0.19
     protester
    0.19
     Gilbert
    0.19
    没人
    0.19
    Activations Density 0.130%

    No Known Activations