© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 55713
    Prev
    Next
    INDEX
    Explanations

    what you mean

    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
     constant
    -0.09
    ji
    -0.08
    ány
    -0.08
     sweep
    -0.08
    _subplot
    -0.07
     Tus
    -0.07
    rap
    -0.07
    anos
    -0.07
    aggio
    -0.07
    rag
    -0.07
    POSITIVE LOGITS
    try
    0.10
     Screens
    0.10
    erm
    0.10
    Exact
    0.09
    chts
    0.09
    rica
    0.09
     exact
    0.09
    era
    0.09
    alth
    0.08
     pard
    0.08
    Activations Density 0.043%

    No Known Activations