© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 61417
    Prev
    Next
    INDEX
    Explanations

    open neighborhoods and subsets

    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
    Negative Logits
     Auditor
    -0.11
     auditor
    -0.09
    æĢ§
    -0.09
     Perr
    -0.09
    trib
    -0.09
     seper
    -0.08
    uars
    -0.08
    igan
    -0.08
    )↵↵↵↵↵↵
    -0.08
    pill
    -0.08
    POSITIVE LOGITS
    unto
    0.09
     subj
    0.08
    itzer
    0.08
    endale
    0.08
     Scient
    0.08
     Sv
    0.08
    agne
    0.08
    lige
    0.08
     fren
    0.08
     "'
    0.08
    Activations Density 0.012%

    No Known Activations