© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 57593
    Prev
    Next
    INDEX
    Explanations

    takes time to build

    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
    hire
    -0.11
     gr
    -0.10
    gia
    -0.10
     bear
    -0.09
     except
    -0.09
    ä½ķ
    -0.09
     departed
    -0.09
    oom
    -0.09
     ASN
    -0.09
     fileprivate
    -0.09
    POSITIVE LOGITS
     complete
    0.07
    git
    0.07
     Hatch
    0.07
    aza
    0.07
     Ih
    0.07
    imore
    0.07
     Complete
    0.07
     Playlist
    0.07
    attles
    0.07
    .Te
    0.07
    Activations Density 0.034%

    No Known Activations