© 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. 3391
    Prev
    Next
    INDEX
    Explanations

    exceptions to generalizations

    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
     Paramount
    -0.09
     w
    -0.09
     damned
    -0.09
    ittel
    -0.09
    /go
    -0.09
     fancy
    -0.08
     punt
    -0.08
    "w
    -0.08
    acic
    -0.08
    inka
    -0.08
    POSITIVE LOGITS
     stereotype
    0.16
     stereotypes
    0.13
     stere
    0.13
     reputation
    0.10
     bad
    0.10
     Ster
    0.10
     exceptions
    0.09
     tarn
    0.09
     Bad
    0.09
     negatives
    0.09
    Activations Density 0.187%

    No Known Activations