© 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. 57100
    Prev
    Next
    INDEX
    Explanations

    calculation requests

    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
    colo
    -0.10
    ibs
    -0.09
     mund
    -0.09
    sap
    -0.09
    ]?.
    -0.09
    immers
    -0.09
    gem
    -0.09
    iol
    -0.09
    suming
    -0.09
    ~=
    -0.09
    POSITIVE LOGITS
    ilee
    0.08
     finally
    0.08
     Tamb
    0.07
    thinkable
    0.07
     also
    0.07
     then
    0.07
    Finally
    0.07
     Finally
    0.07
    etta
    0.07
    Validity
    0.07
    Activations Density 0.052%

    No Known Activations