© 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. 3354
    Prev
    Next
    INDEX
    Explanations

    programming 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
    æīĵçĿĢ
    -0.20
    çŨ
    -0.19
    .ht
    -0.18
    çŀ¿
    -0.18
    /gpio
    -0.18
    .AppendFormat
    -0.18
    .getTransaction
    -0.18
    /inet
    -0.18
     Colleg
    -0.18
    NibName
    -0.18
    POSITIVE LOGITS
    éĴ¬
    0.21
     {{--<
    0.21
    «
    0.20
    velt
    0.20
    ">$
    0.19
    <HashMap
    0.19
    µľ
    0.19
    datable
    0.18
    NSMutableDictionary
    0.18
     PureComponent
    0.18
    Activations Density 0.001%

    No Known Activations