© 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. 56546
    Prev
    Next
    INDEX
    Explanations

    the highest, the best, the potential

    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
     needed
    -0.10
    got
    -0.10
     Needed
    -0.10
    needed
    -0.09
     got
    -0.09
     missing
    -0.09
     necessary
    -0.09
    Needed
    -0.08
    pin
    -0.08
     lacked
    -0.08
    POSITIVE LOGITS
     possibility
    0.12
     natur
    0.09
    odor
    0.09
    undy
    0.09
    imes
    0.09
     POSSIBILITY
    0.09
    wg
    0.08
    occ
    0.08
    erp
    0.08
     yr
    0.08
    Activations Density 0.041%

    No Known Activations