© 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. 58374
    Prev
    Next
    INDEX
    Explanations

    code constructs like `];` and `identifier`

    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
     Moo
    -0.08
     Trev
    -0.08
    /File
    -0.08
    .idx
    -0.08
    uria
    -0.08
     Unicorn
    -0.08
    bout
    -0.08
    uan
    -0.07
     numbering
    -0.07
    ogue
    -0.07
    POSITIVE LOGITS
    éré
    0.09
    ISC
    0.09
    unks
    0.09
    illac
    0.09
    asics
    0.08
    igen
    0.08
    hin
    0.08
     movers
    0.08
    ment
    0.08
     Kits
    0.08
    Activations Density 0.009%

    No Known Activations