© 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. 2312
    Prev
    Next
    INDEX
    Explanations

    web .com sites

    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
     nature
    -0.10
     Tol
    -0.09
    475
    -0.08
     ones
    -0.07
     Totally
    -0.07
     explorer
    -0.07
     largest
    -0.07
    OTA
    -0.07
    åŁ
    -0.07
    åĪĹ
    -0.07
    POSITIVE LOGITS
     Comm
    0.09
    ÑĢаз
    0.09
    egov
    0.09
     IMG
    0.08
    lian
    0.08
    rome
    0.08
    adh
    0.08
    rox
    0.08
    ió
    0.08
    led
    0.08
    Activations Density 0.513%

    No Known Activations