© 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. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 1935
    Prev
    Next
    INDEX
    Explanations

    unit or concept

    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
    .timing
    -0.08
    vang
    -0.08
    .Panel
    -0.08
    .myapplication
    -0.08
    eme
    -0.08
    apon
    -0.08
    Ł¥
    -0.08
    apsible
    -0.08
     FG
    -0.08
     pic
    -0.07
    POSITIVE LOGITS
     wise
    0.10
    -wise
    0.10
    à¹Į
    0.09
    wise
    0.09
     Khan
    0.08
     Brut
    0.08
    mol
    0.08
     educated
    0.07
     Ent
    0.07
    ãĤģ
    0.07
    Activations Density 3.876%

    No Known Activations