© 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. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 3945
    Prev
    Next
    INDEX
    Explanations

    json.dumps, .google.com, django.middleware

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     covid
    -0.17
     COVID
    -0.17
    COVID
    -0.16
    202
    -0.16
     ðĿ
    -0.14
     ðŁ
    -0.14
     Biden
    -0.14
    #:
    -0.14
     ðŁij
    -0.13
     Covid
    -0.13
    POSITIVE LOGITS
     http
    0.13
    http
    0.11
     Pou
    0.11
    (http
    0.10
     iPod
    0.09
     prostitute
    0.09
    atin
    0.09
     Obama
    0.09
    ATA
    0.09
    اس
    0.09
    Activations Density 2.386%

    No Known Activations