© 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. 2260
    Prev
    Next
    INDEX
    Explanations

    knew / knew that

    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
    -outline
    -0.10
     catch
    -0.09
    inaire
    -0.09
    aye
    -0.08
     historical
    -0.08
    istogram
    -0.08
    stantiate
    -0.08
    oes
    -0.08
    _gray
    -0.08
    andum
    -0.08
    POSITIVE LOGITS
     knew
    0.09
    çŁ¥
    0.09
    knowledge
    0.09
     kok
    0.09
     Ment
    0.09
     Knowledge
    0.08
    bj
    0.08
     Correspond
    0.08
     Buzz
    0.08
     Rush
    0.08
    Activations Density 0.259%

    No Known Activations