© 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. 57708
    Prev
    Next
    INDEX
    Explanations

    encouraged, credit, suggests, hand, classrooms

    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
     Hen
    -0.09
    -0.08
    <|fim_middle|>
    -0.08
     controvers
    -0.07
    Embed
    -0.07
    ictions
    -0.07
    âĢIJ
    -0.07
    ."↵↵
    -0.07
     notably
    -0.07
    .↵↵
    -0.07
    POSITIVE LOGITS
    .Reflection
    0.09
    .Private
    0.09
    ,!
    0.09
    .Raw
    0.09
    ì°
    0.09
     tion
    0.09
    OLLOW
    0.09
    loser
    0.08
    imeline
    0.08
    antha
    0.08
    Activations Density 0.031%

    No Known Activations