© 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. 2570
    Prev
    Next
    INDEX
    Explanations

    site mentions cookies, management, assessment, bank

    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
     suspect
    -0.10
     suspects
    -0.09
     seks
    -0.09
    ENO
    -0.08
    532
    -0.08
     senators
    -0.08
     Bunny
    -0.08
     scheduled
    -0.08
     scream
    -0.07
    scheduled
    -0.07
    POSITIVE LOGITS
    (SS
    0.12
    (SP
    0.11
    (SE
    0.10
    illance
    0.09
    inel
    0.09
    mund
    0.09
    -Identifier
    0.09
    (SC
    0.09
     Bethlehem
    0.08
     giÃł
    0.08
    Activations Density 4.420%

    No Known Activations