© 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. 55809
    Prev
    Next
    INDEX
    Explanations

    sentencing hearing, date, phase

    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
    stor
    -0.09
    ed
    -0.09
    nez
    -0.09
     outdoors
    -0.09
    WF
    -0.08
     posto
    -0.08
    hawk
    -0.08
    uggage
    -0.08
    óg
    -0.08
    iec
    -0.08
    POSITIVE LOGITS
    bonus
    0.09
    ipur
    0.09
    ora
    0.09
    ibur
    0.08
    imb
    0.08
    hall
    0.08
    ju
    0.08
    emark
    0.08
    ita
    0.08
    atter
    0.08
    Activations Density 0.001%

    No Known Activations