© 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. 57711
    Prev
    Next
    INDEX
    Explanations

    non-invasive, equilibrium, composable, pathogenic

    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
     Dew
    -0.09
     hyp
    -0.08
     Blink
    -0.08
     BG
    -0.08
    ikk
    -0.08
    ij
    -0.08
    dh
    -0.08
    afe
    -0.08
     conservative
    -0.07
     secre
    -0.07
    POSITIVE LOGITS
    tur
    0.11
    -analytics
    0.09
    mai
    0.09
    zia
    0.09
     Mach
    0.09
    -In
    0.09
     Elo
    0.08
    ocos
    0.08
    ène
    0.08
     Tur
    0.08
    Activations Density 0.035%

    No Known Activations