© 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. 58060
    Prev
    Next
    INDEX
    Explanations

    used as / for / by

    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
     DEST
    -0.09
    EDA
    -0.08
    ubber
    -0.07
     Applications
    -0.07
     Hear
    -0.07
     Norman
    -0.07
    Ñıд
    -0.07
     WOW
    -0.07
    aday
    -0.07
     ris
    -0.07
    POSITIVE LOGITS
     Pike
    0.10
    ICC
    0.09
     boarding
    0.09
    Æ°
    0.09
     Gathering
    0.09
     (!_
    0.09
     internal
    0.09
    /Register
    0.09
    .until
    0.09
    ascript
    0.09
    Activations Density 0.050%

    No Known Activations