© 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. 1708
    Prev
    Next
    INDEX
    Explanations

    altered factor dysfunction deficient associated

    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
    -exp
    -0.09
    Ether
    -0.09
     nominal
    -0.09
     informal
    -0.09
     completeness
    -0.09
     fixation
    -0.09
     designated
    -0.09
    inform
    -0.08
     mening
    -0.08
     simplest
    -0.08
    POSITIVE LOGITS
     links
    0.13
     Links
    0.13
     link
    0.13
     mod
    0.12
     chron
    0.12
     markers
    0.12
     correlated
    0.12
     increased
    0.11
     correlations
    0.11
     implicated
    0.11
    Activations Density 3.643%

    No Known Activations