© 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. 1791
    Prev
    Next
    INDEX
    Explanations

    lists ending in etc or commas

    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
     itself
    -0.11
     namely
    -0.09
    ãĤĦ
    -0.09
     viz
    -0.09
     strtoupper
    -0.09
     consisting
    -0.09
    —one
    -0.08
    —from
    -0.08
     pal
    -0.08
     bu
    -0.07
    POSITIVE LOGITS
     respectively
    0.32
     respective
    0.22
    éĥ½
    0.21
     alike
    0.21
    —all
    0.20
     gibi
    0.19
    respect
    0.19
    etc
    0.19
     etc
    0.18
    collect
    0.14
    Activations Density 2.937%

    No Known Activations