© 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. 1343
    Prev
    Next
    INDEX
    Explanations

    REO Speedwagon, Pinhead Gunpowder, BigBadToyStore

    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
     misunder
    -0.10
     unre
    -0.09
     Vul
    -0.08
     Oaks
    -0.08
    Ĥ¹
    -0.08
     dung
    -0.08
    <td
    -0.07
     accuse
    -0.07
    quo
    -0.07
     McN
    -0.07
    POSITIVE LOGITS
     ={↵
    0.10
    ivr
    0.07
     gul
    0.07
    ummings
    0.07
    ürnberg
    0.07
    noticed
    0.07
    .Autowired
    0.07
    ])**
    0.07
    LOWER
    0.07
     beneficiary
    0.07
    Activations Density 4.692%

    No Known Activations