© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115255
    Prev
    Next
    INDEX
    Explanations

    Spanish ending suffixes

    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
     Compression
    -0.11
    kok
    -0.10
     blow
    -0.10
     TAR
    -0.10
     Oper
    -0.10
    ity
    -0.09
     Makeup
    -0.09
    eti
    -0.09
     smack
    -0.09
    obe
    -0.09
    POSITIVE LOGITS
    bos
    0.09
    icha
    0.09
    oner
    0.09
     stage
    0.08
    ices
    0.08
     reclaimed
    0.08
    andid
    0.08
     peripheral
    0.08
    DataManager
    0.08
    cki
    0.08
    Activations Density 0.020%

    No Known Activations