© 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. 54724
    Prev
    Next
    INDEX
    Explanations

    ashamed, important, thank, what

    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
     catching
    -0.12
    ckt
    -0.11
     catch
    -0.10
     dip
    -0.09
     Herman
    -0.09
    iring
    -0.09
    EDI
    -0.09
    reas
    -0.09
     reassuring
    -0.09
     conven
    -0.09
    POSITIVE LOGITS
    kok
    0.09
     polar
    0.09
     Closure
    0.09
     now
    0.09
     sentence
    0.09
     vind
    0.08
     Consum
    0.08
     finally
    0.08
     closure
    0.08
     famil
    0.08
    Activations Density 0.038%

    No Known Activations