© 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. 56334
    Prev
    Next
    INDEX
    Explanations

    apologies and explanations

    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
     Sno
    -0.10
    depart
    -0.10
     Hector
    -0.10
    Suppress
    -0.10
     Hog
    -0.09
     Rated
    -0.09
     Hof
    -0.09
    -cont
    -0.09
    /assert
    -0.09
    ime
    -0.09
    POSITIVE LOGITS
     FIXED
    0.09
     apologize
    0.09
     Riv
    0.08
     resend
    0.08
    trying
    0.08
     rect
    0.08
     traged
    0.08
     obe
    0.08
     apologise
    0.08
     messed
    0.08
    Activations Density 0.059%

    No Known Activations