© 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. 3309
    Prev
    Next
    INDEX
    Explanations

    methods, participants, education, discovery, project

    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
    ibu
    -0.10
    OOT
    -0.10
    afa
    -0.10
     closed
    -0.09
     circa
    -0.08
    ovich
    -0.08
     »↵↵
    -0.08
    .live
    -0.08
    oto
    -0.08
    [code
    -0.08
    POSITIVE LOGITS
    ichen
    0.08
     Brid
    0.08
    niest
    0.08
    asmine
    0.08
    nds
    0.07
    ])+
    0.07
    igmat
    0.07
     philosophy
    0.07
    ObjectId
    0.07
    .crypto
    0.07
    Activations Density 0.041%

    No Known Activations