© 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. 1212
    Prev
    Next
    INDEX
    Explanations

    html view path

    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
    opy
    -0.09
     Mines
    -0.08
     Phil
    -0.08
     gé
    -0.08
    Para
    -0.08
    (android
    -0.08
    Fed
    -0.08
     hanging
    -0.08
     hyp
    -0.08
     coal
    -0.08
    POSITIVE LOGITS
    lix
    0.10
     Baxter
    0.10
    acades
    0.09
     brides
    0.09
    à¸Ĥ
    0.09
    lash
    0.09
    orum
    0.09
    loy
    0.09
    onic
    0.08
    ripp
    0.08
    Activations Density 4.699%

    No Known Activations