© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 961
    Prev
    Next
    INDEX
    Explanations

    than other/usual

    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
    ýt
    -0.11
    instead
    -0.10
     Winn
    -0.10
     instead
    -0.10
    ado
    -0.10
     extraordin
    -0.10
    Ĺı
    -0.09
    <small
    -0.09
     nud
    -0.09
    pty
    -0.09
    POSITIVE LOGITS
     other
    0.19
     counterparts
    0.18
     usual
    0.17
     conventional
    0.17
     traditional
    0.16
     typical
    0.15
     previous
    0.15
     others
    0.14
    åħ¶ä»ĸ
    0.14
     counterpart
    0.13
    Activations Density 1.294%

    No Known Activations