© 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. 1293
    Prev
    Next
    INDEX
    Explanations

    counting prefixes (multi-, double-, triple-, quad-)

    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
    osit
    -0.10
     Aires
    -0.09
     kre
    -0.09
    olean
    -0.09
    allo
    -0.09
    psc
    -0.09
    orr
    -0.09
    ael
    -0.09
    flux
    -0.09
    iland
    -0.08
    POSITIVE LOGITS
    /single
    0.14
    /qu
    0.14
    /tr
    0.13
     sided
    0.13
    .parseDouble
    0.13
    ts
    0.11
    -sided
    0.11
    ided
    0.11
    /div
    0.10
     sclerosis
    0.10
    Activations Density 1.299%

    No Known Activations