© 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. 57409
    Prev
    Next
    INDEX
    Explanations

    next to

    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
    лÑİ
    -0.11
    еÑĢж
    -0.10
    (math
    -0.09
    .jav
    -0.09
    adores
    -0.09
    ateurs
    -0.09
     Chip
    -0.09
     pis
    -0.09
    nis
    -0.09
    =""/>↵
    -0.09
    POSITIVE LOGITS
     isolation
    0.08
     isol
    0.08
     Casinos
    0.08
    -area
    0.07
    uster
    0.07
    rah
    0.07
     civilizations
    0.07
    erox
    0.07
    oyo
    0.07
     isolated
    0.07
    Activations Density 0.091%

    No Known Activations