© 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. 8597
    Prev
    Next
    INDEX
    Explanations

    TAG = value

    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
     gro
    -0.07
     haul
    -0.07
     dent
    -0.06
    boo
    -0.06
    -One
    -0.06
    ز
    -0.06
     autonomous
    -0.06
     easily
    -0.06
     larg
    -0.06
    idf
    -0.06
    POSITIVE LOGITS
     sécur
    0.11
     Raised
    0.11
     Expanded
    0.11
     rpt
    0.10
     Presented
    0.10
    ature
    0.10
     warrant
    0.10
    untu
    0.10
     jury
    0.10
     fresh
    0.10
    Activations Density 0.449%

    No Known Activations