© 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. 4704
    Prev
    Next
    INDEX
    Explanations

    changes or preservation

    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
     wakeup
    -0.11
     schö
    -0.10
     hookup
    -0.10
     continental
    -0.10
    olen
    -0.10
    "group
    -0.10
    Terminal
    -0.10
    ramer
    -0.09
    flux
    -0.09
     Felix
    -0.09
    POSITIVE LOGITS
     preserves
    0.14
     changes
    0.14
     altered
    0.14
     preserve
    0.13
     preserving
    0.13
     revert
    0.12
     retaining
    0.12
     preserved
    0.12
     retain
    0.11
     reverted
    0.11
    Activations Density 0.460%

    No Known Activations