© 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. 113741
    Prev
    Next
    INDEX
    Explanations

    as expected, as always

    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
    uku
    -0.09
    Php
    -0.09
    ัà¸Ļ
    -0.09
    726
    -0.09
     Mais
    -0.09
    ANE
    -0.09
    oS
    -0.09
    303
    -0.08
     Cottage
    -0.08
    jian
    -0.08
    POSITIVE LOGITS
     usual
    0.69
    usual
    0.45
     always
    0.43
    always
    0.35
     ALWAYS
    0.34
     Always
    0.34
    Always
    0.32
     customary
    0.31
     sempre
    0.27
     usually
    0.27
    Activations Density 0.178%

    No Known Activations