© 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. 57215
    Prev
    Next
    INDEX
    Explanations

    reportedly

    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
     announces
    -0.11
     announcing
    -0.10
    fy
    -0.10
     announced
    -0.10
     announcements
    -0.10
     announcement
    -0.09
    onestly
    -0.09
    513
    -0.09
     DECLARE
    -0.09
    press
    -0.08
    POSITIVE LOGITS
     reportedly
    0.11
     internally
    0.11
     secretly
    0.10
     dag
    0.10
     privately
    0.09
     allegedly
    0.09
    /internal
    0.09
     Tro
    0.08
     tro
    0.08
     locally
    0.08
    Activations Density 0.125%

    No Known Activations