© 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. 4044
    Prev
    Next
    INDEX
    Explanations

    affirmative or emphatic responses

    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
    @student
    -0.10
     brush
    -0.09
     Hat
    -0.09
     nec
    -0.09
    walker
    -0.09
     doch
    -0.08
    arent
    -0.08
    /admin
    -0.08
    asename
    -0.08
    acr
    -0.08
    POSITIVE LOGITS
     mega
    0.10
    onestly
    0.09
     Definitely
    0.09
     firstly
    0.09
     Firstly
    0.08
     Absolutely
    0.08
     absolutely
    0.08
     pin
    0.08
    iola
    0.08
    ijn
    0.08
    Activations Density 0.088%

    No Known Activations