© 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. 4569
    Prev
    Next
    INDEX
    Explanations

    Fernando and names with 'ando' suffix

    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
     Cove
    -0.10
     humble
    -0.10
    iteur
    -0.10
    ITA
    -0.09
    OI
    -0.09
    itched
    -0.09
     Literal
    -0.09
     helpers
    -0.09
    inia
    -0.09
     Ebook
    -0.08
    POSITIVE LOGITS
    atori
    0.09
     Trim
    0.09
     bury
    0.09
     Rath
    0.08
    uish
    0.08
     venture
    0.08
     Nah
    0.08
     Moore
    0.08
    onder
    0.08
     interes
    0.08
    Activations Density 0.001%

    No Known Activations