© 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. 54830
    Prev
    Next
    INDEX
    Explanations

    MOF or chemical structures

    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
     Pet
    -0.08
     energetic
    -0.08
     etc
    -0.08
     flow
    -0.07
    Pet
    -0.07
     Dw
    -0.07
     '['
    -0.07
     incentiv
    -0.07
     pen
    -0.07
     —
    -0.07
    POSITIVE LOGITS
    amu
    0.12
    villa
    0.10
    /light
    0.10
    bucks
    0.10
     Bun
    0.10
    YRO
    0.10
    chl
    0.10
    --[
    0.10
    vale
    0.10
    .Port
    0.10
    Activations Density 0.089%

    No Known Activations