© 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. 1915
    Prev
    Next
    INDEX
    Explanations

    wearing white

    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
     desired
    -0.09
    /add
    -0.09
     busty
    -0.09
     notoriously
    -0.08
     better
    -0.08
    /create
    -0.08
    upp
    -0.08
     fleece
    -0.08
     troublesome
    -0.08
     rico
    -0.08
    POSITIVE LOGITS
     appeared
    0.15
     Appears
    0.14
     prominently
    0.14
     appearing
    0.13
     appears
    0.13
     resembling
    0.12
     seemed
    0.12
     reminiscent
    0.12
     white
    0.12
     appear
    0.12
    Activations Density 1.624%

    No Known Activations