© 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. 58480
    Prev
    Next
    INDEX
    Explanations

    copyright followed by parenthesis

    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
    andid
    -0.09
    Ahead
    -0.09
    ends
    -0.09
    antic
    -0.09
    ites
    -0.09
    enschaft
    -0.09
     Paz
    -0.08
     passage
    -0.08
     forth
    -0.08
    âĢİ
    -0.08
    POSITIVE LOGITS
    odore
    0.09
     Mori
    0.08
    наÑĩ
    0.08
     Dayton
    0.08
    ilik
    0.08
     pare
    0.08
     dut
    0.07
    dff
    0.07
    inel
    0.07
     staring
    0.07
    Activations Density 0.081%

    No Known Activations