© 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. 2100
    Prev
    Next
    INDEX
    Explanations

    code and technical text

    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
    rne
    -0.21
    ForeColor
    -0.21
    roupe
    -0.19
    ([]*
    -0.19
    inja
    -0.19
    Sender
    -0.19
    NullException
    -0.18
     D
    -0.18
    indsight
    -0.18
    å»¶è¿Ł
    -0.18
    POSITIVE LOGITS
    ï¼ģ');↵
    0.23
    irlines
    0.23
    .CG
    0.23
     Sexo
    0.22
    #ac
    0.22
    .DAL
    0.21
    bourg
    0.21
     addCriterion
    0.21
    NU
    0.21
    ');?></
    0.20
    Activations Density 0.001%

    No Known Activations