© 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. 2965
    Prev
    Next
    INDEX
    Explanations

    then followed by a consequence

    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
     then
    -0.24
    then
    -0.21
    Then
    -0.21
    	then
    -0.18
     Then
    -0.18
    _then
    -0.16
    THEN
    -0.15
     THEN
    -0.15
     now
    -0.12
     thereafter
    -0.12
    POSITIVE LOGITS
    umber
    0.15
    ewe
    0.11
    -current
    0.11
    ouve
    0.11
    oner
    0.11
    moz
    0.10
    ìĦľ
    0.10
     aber
    0.10
    etwork
    0.09
    onus
    0.09
    Activations Density 0.099%

    No Known Activations