© 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. 4486
    Prev
    Next
    INDEX
    Explanations

    #define directives after )

    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
    roots
    -0.08
    .git
    -0.08
    iras
    -0.07
    elder
    -0.07
    'icon
    -0.07
    ½æķ°
    -0.07
     NSNumber
    -0.07
     Andrews
    -0.07
    exports
    -0.07
    obl
    -0.07
    POSITIVE LOGITS
     MF
    0.11
    MF
    0.09
     stip
    0.09
     mf
    0.09
    agens
    0.09
    .EventQueue
    0.09
    caf
    0.09
     spree
    0.09
    fas
    0.08
    leaning
    0.08
    Activations Density 0.036%

    No Known Activations