© 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. 56791
    Prev
    Next
    INDEX
    Explanations

    free time

    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
     unpack
    -0.08
     pil
    -0.08
    emen
    -0.07
    umu
    -0.07
     Conte
    -0.07
     embrace
    -0.07
     embraces
    -0.07
     rupture
    -0.07
    antity
    -0.07
    Booking
    -0.07
    POSITIVE LOGITS
     leisure
    0.16
     hobby
    0.14
     spor
    0.14
     weekends
    0.14
     intermittent
    0.14
     casually
    0.13
     Leisure
    0.13
     volunteer
    0.13
     volunteers
    0.13
     casual
    0.12
    Activations Density 0.140%

    No Known Activations