© 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. 54733
    Prev
    Next
    INDEX
    Explanations

    overflow behavior and errors

    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
    èµ·
    -0.11
    oba
    -0.10
    oya
    -0.09
    bourne
    -0.09
    mot
    -0.09
    won
    -0.09
    zin
    -0.09
    cast
    -0.09
     apl
    -0.09
    min
    -0.09
    POSITIVE LOGITS
     neat
    0.09
    Traditional
    0.09
     Traditional
    0.08
    ات
    0.08
     forth
    0.08
    als
    0.07
    æº
    0.07
    клÑİÑĩ
    0.07
    æł¼
    0.07
    ku
    0.07
    Activations Density 0.011%

    No Known Activations