© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 2118
    Prev
    Next
    INDEX
    Explanations

    explaining findings and predictions

    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
     hect
    -0.08
     Att
    -0.08
    iac
    -0.08
     Research
    -0.08
    /native
    -0.08
    ritte
    -0.08
    solete
    -0.08
     regrets
    -0.08
    QUAL
    -0.07
     ansible
    -0.07
    POSITIVE LOGITS
     consistent
    0.12
     theoretically
    0.11
     consistency
    0.10
     expectation
    0.10
    consistent
    0.10
     inconsistent
    0.10
     predicted
    0.10
     Expect
    0.10
     expected
    0.09
     implying
    0.09
    Activations Density 0.250%

    No Known Activations