© 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. 1548
    Prev
    Next
    INDEX
    Explanations

    associated with, responsible for

    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
    ò
    -0.12
     converse
    -0.11
    thumbs
    -0.11
     ashes
    -0.11
    ке
    -0.11
    ersist
    -0.11
    lé
    -0.11
     Ish
    -0.10
    dde
    -0.10
    Hallo
    -0.10
    POSITIVE LOGITS
    äºİ
    0.09
    <td
    0.07
     Aster
    0.06
     cref
    0.06
    ↵↵    ↵
    0.05
    ][_
    0.05
    $__
    0.05
     qual
    0.05
    ↵        ↵        ↵
    0.05
    ig
    0.05
    Activations Density 3.021%

    No Known Activations