© 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. 58568
    Prev
    Next
    INDEX
    Explanations

    languages

    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
     Continent
    -0.10
     continent
    -0.10
     contemporary
    -0.09
    chl
    -0.08
     Complete
    -0.08
    eba
    -0.08
    iec
    -0.08
    kees
    -0.08
    -us
    -0.08
    ÑĢем
    -0.08
    POSITIVE LOGITS
     asi
    0.09
     w
    0.09
    kit
    0.08
     Lew
    0.08
    çī
    0.08
    icio
    0.07
    romo
    0.07
     pl
    0.07
    aire
    0.07
     acknowledgement
    0.07
    Activations Density 0.018%

    No Known Activations