© 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. 1595
    Prev
    Next
    INDEX
    Explanations

    glad, bad, or sad feelings

    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
     Household
    -0.11
    Arm
    -0.10
     seriously
    -0.10
     deserves
    -0.10
     amore
    -0.10
     buckle
    -0.10
    nage
    -0.10
    .createFrom
    -0.10
    esson
    -0.10
     deserved
    -0.10
    POSITIVE LOGITS
     having
    0.10
     choices
    0.08
     hearing
    0.08
    èĥ½
    0.08
     seeing
    0.08
     choice
    0.08
     Able
    0.07
     finally
    0.07
     able
    0.07
     fact
    0.07
    Activations Density 1.111%

    No Known Activations