© 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. 54778
    Prev
    Next
    INDEX
    Explanations

    percentages and units

    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
    ets
    -0.09
     Gund
    -0.08
    ego
    -0.08
    acle
    -0.08
    uv
    -0.07
     Duffy
    -0.07
     pis
    -0.07
    etable
    -0.07
     unlink
    -0.07
     Gard
    -0.07
    POSITIVE LOGITS
    ย
    0.10
    ency
    0.10
     Entr
    0.10
    rig
    0.10
    gers
    0.10
    otron
    0.09
    -ed
    0.09
     combin
    0.09
    erd
    0.09
    ettel
    0.09
    Activations Density 0.009%

    No Known Activations