© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 55130
    Prev
    Next
    INDEX
    Explanations

    list items starting new concepts

    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
     thru
    -0.10
     particulars
    -0.09
     totally
    -0.09
     gaz
    -0.08
     TAM
    -0.08
    Jump
    -0.08
    corner
    -0.08
     Mom
    -0.08
     Maritime
    -0.08
    bro
    -0.07
    POSITIVE LOGITS
     government
    0.11
    odb
    0.10
     Bast
    0.09
     Kane
    0.09
    spiel
    0.09
    ILI
    0.09
    kart
    0.09
    Government
    0.09
    Compat
    0.09
    gang
    0.09
    Activations Density 0.018%

    No Known Activations