© 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. 1011
    Prev
    Next
    INDEX
    Explanations

    former author

    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
     unw
    -0.10
    fans
    -0.09
    bjerg
    -0.09
    ichier
    -0.08
     aides
    -0.08
     reporters
    -0.08
     amateurs
    -0.08
    ants
    -0.08
     idiots
    -0.08
    cken
    -0.08
    POSITIVE LOGITS
     former
    0.17
     retired
    0.13
     member
    0.13
     formerly
    0.13
     renowned
    0.12
    -turned
    0.12
     founding
    0.12
    former
    0.12
     accomplished
    0.12
     managing
    0.11
    Activations Density 2.776%

    No Known Activations