© 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. 49156
    Prev
    Next
    INDEX
    Explanations

    quoted text indicator

    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
     ras
    -0.09
    ieder
    -0.09
    aden
    -0.09
     Fin
    -0.09
     crack
    -0.09
    avec
    -0.08
    Activ
    -0.08
     hors
    -0.08
     Pey
    -0.08
    azon
    -0.08
    POSITIVE LOGITS
    mia
    0.10
    -aligned
    0.10
    tog
    0.10
     act
    0.09
     vacancy
    0.09
    tant
    0.09
     emphas
    0.09
    ombat
    0.09
    .cgi
    0.09
    -ish
    0.09
    Activations Density 0.035%

    No Known Activations