© 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. 8451
    Prev
    Next
    INDEX
    Explanations

    names like Keyondra Lockett, Fritz, Claude Davis

    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
    upal
    -0.09
    opi
    -0.09
    rac
    -0.08
    rid
    -0.08
     Parkway
    -0.08
    eler
    -0.08
     ord
    -0.08
    uste
    -0.07
     Hubbard
    -0.07
    .pad
    -0.07
    POSITIVE LOGITS
     неÑĤ
    0.09
     Mines
    0.08
     aside
    0.08
    âĢ¦the
    0.08
    Minus
    0.08
    azzi
    0.08
    UF
    0.08
    aston
    0.07
     laugh
    0.07
    âĢ¦I
    0.07
    Activations Density 0.932%

    No Known Activations