© 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-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 47527
    Prev
    Next
    INDEX
    Explanations

    lesson and property declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    prar
    -0.10
    rå
    -0.10
    quil
    -0.10
    .tc
    -0.09
    zá
    -0.09
    velt
    -0.09
    contra
    -0.09
    vro
    -0.09
    veh
    -0.09
     Straw
    -0.09
    POSITIVE LOGITS
     Secret
    0.10
     estate
    0.09
     Hutchinson
    0.09
    stants
    0.09
     Marino
    0.09
     POW
    0.08
     Sisters
    0.08
     again
    0.08
     Estate
    0.08
     kut
    0.08
    Activations Density 0.001%

    No Known Activations