© 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. 4232
    Prev
    Next
    INDEX
    Explanations

    to + verb

    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
    a
    -0.09
     perfection
    -0.07
    ssa
    -0.07
    а
    -0.07
    nam
    -0.07
    orate
    -0.07
     quality
    -0.07
    umbs
    -0.06
    ands
    -0.06
    sw
    -0.06
    POSITIVE LOGITS
    mpr
    0.10
    stry
    0.10
    ime
    0.10
    nton
    0.10
     inability
    0.10
     hear
    0.10
    ¥
    0.10
    rang
    0.10
    ered
    0.10
     Thornton
    0.10
    Activations Density 0.243%

    No Known Activations