© 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. 1612
    Prev
    Next
    INDEX
    Explanations

    film director, filmmaker, artist, playwright

    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
     announc
    -0.08
    ichi
    -0.08
     Oktober
    -0.08
     masc
    -0.08
     default
    -0.08
     sung
    -0.07
     logically
    -0.07
    relude
    -0.07
     forfe
    -0.07
    /save
    -0.07
    POSITIVE LOGITS
     prolific
    0.17
     writing
    0.16
     artistic
    0.16
     stylist
    0.15
     works
    0.15
    /art
    0.14
     producing
    0.14
     creations
    0.14
     creative
    0.14
     productions
    0.13
    Activations Density 2.471%

    No Known Activations