© 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. 54773
    Prev
    Next
    INDEX
    Explanations

    foliation, contour lines, fiber products, slice

    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
     paving
    -0.07
    bridge
    -0.07
     pav
    -0.07
    æĹ
    -0.07
     monitors
    -0.07
     paved
    -0.07
    am
    -0.06
     Tud
    -0.06
     bro
    -0.06
     Sciences
    -0.06
    POSITIVE LOGITS
     equip
    0.10
    .colorbar
    0.10
     fert
    0.10
     TOUCH
    0.10
     Thickness
    0.10
    hots
    0.10
    ãĥ¬
    0.10
     bearing
    0.10
    .ACT
    0.10
    SPATH
    0.10
    Activations Density 0.022%

    No Known Activations