© 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. 1153
    Prev
    Next
    INDEX
    Explanations

    completeness or importance

    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
     “[
    -0.15
     incentiv
    -0.14
    —including
    -0.14
     newfound
    -0.14
     potentially
    -0.14
     transitioning
    -0.13
     overly
    -0.13
     priorit
    -0.13
     upfront
    -0.13
    Âł
    -0.13
    POSITIVE LOGITS
    ,—
    0.19
     peculiar
    0.15
     equipments
    0.14
     negro
    0.14
     endeavour
    0.12
     chiefly
    0.12
     diversos
    0.12
     furnished
    0.11
     tho
    0.11
     machinery
    0.11
    Activations Density 2.967%

    No Known Activations