© 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. 3818
    Prev
    Next
    INDEX
    Explanations

    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
     deter
    -0.09
    orer
    -0.09
    BER
    -0.09
     controls
    -0.09
    gross
    -0.09
    ook
    -0.08
    berg
    -0.08
     Volunteer
    -0.08
    otics
    -0.08
    ames
    -0.08
    POSITIVE LOGITS
    é¢
    0.09
    eba
    0.09
     Chall
    0.09
    eon
    0.08
     explode
    0.08
     PU
    0.08
    |array
    0.08
     Cv
    0.08
    avian
    0.08
    _that
    0.08
    Activations Density 0.108%

    No Known Activations