© 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. 54951
    Prev
    Next
    INDEX
    Explanations

    code delimiters and keywords

    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
    rose
    -0.09
    ikan
    -0.09
    ISK
    -0.08
    Liked
    -0.08
    amazon
    -0.08
     Gregg
    -0.08
    erman
    -0.08
    icos
    -0.08
    rij
    -0.08
     voiced
    -0.08
    POSITIVE LOGITS
    afs
    0.08
    iram
    0.08
    orris
    0.08
    roller
    0.08
     Bez
    0.08
     commod
    0.08
     aliens
    0.08
     alien
    0.08
     Mount
    0.08
     Coil
    0.08
    Activations Density 0.002%

    No Known Activations