© 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. 1989
    Prev
    Next
    INDEX
    Explanations

    Monthly Archives:

    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
    <|fim_suffix|>
    -0.10
    ċ
    -0.09
     ”
    -0.09
    -heading
    -0.09
    âĢ¦.
    -0.09
    ewise
    -0.09
    (!
    -0.08
    äs
    -0.08
     internally
    -0.08
    inals
    -0.08
    POSITIVE LOGITS
     ,↵↵
    0.13
     âĨĴ↵↵
    0.12
    /component
    0.11
     |↵↵
    0.11
    permalink
    0.10
    âĢ¢↵↵
    0.10
    +↵↵
    0.09
     Administrator
    0.09
     »↵↵
    0.09
     >↵↵
    0.09
    Activations Density 2.210%

    No Known Activations