© 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. 58371
    Prev
    Next
    INDEX
    Explanations

    legal citations (§)

    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
    coal
    -0.09
    andr
    -0.08
     Goods
    -0.08
    iT
    -0.08
    prompt
    -0.07
     Bru
    -0.07
    uppe
    -0.07
    eturn
    -0.07
    arius
    -0.07
    .reader
    -0.07
    POSITIVE LOGITS
    eil
    0.10
     Barney
    0.10
    çĽ
    0.10
     persuasion
    0.10
    OrDefault
    0.10
    rans
    0.10
    hai
    0.09
     Pers
    0.09
    ensis
    0.09
     Rodney
    0.09
    Activations Density 0.003%

    No Known Activations