© 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. 58658
    Prev
    Next
    INDEX
    Explanations

    defined or enabled

    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
    acks
    -0.10
    ãĤĮ
    -0.10
     mute
    -0.09
    REA
    -0.09
     Lyons
    -0.09
    edom
    -0.08
    imus
    -0.08
    oton
    -0.08
    osto
    -0.08
    áo
    -0.08
    POSITIVE LOGITS
     diss
    0.09
    ople
    0.08
    isel
    0.08
     Carp
    0.08
    ayers
    0.08
    iced
    0.08
    aho
    0.08
     Accident
    0.08
    _album
    0.07
     (()
    0.07
    Activations Density 0.012%

    No Known Activations