© 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. 1929
    Prev
    Next
    INDEX
    Explanations

    definition, following, conclusion

    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
    -esque
    -0.14
     policym
    -0.13
     neighbouring
    -0.13
     “[
    -0.12
     badass
    -0.11
    —which
    -0.11
    -0.11
     [...]↵↵
    -0.11
    halb
    -0.11
     incredibly
    -0.11
    POSITIVE LOGITS
     thru
    0.16
     herein
    0.10
    Persons
    0.10
     alas
    0.09
     wisely
    0.09
     needing
    0.09
     cog
    0.08
     perhaps
    0.08
     anew
    0.08
     insure
    0.08
    Activations Density 4.981%

    No Known Activations