© 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. 32125
    Prev
    Next
    INDEX
    Explanations

    words ending in 's' or 'te'

    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
    Č
    -0.11
     Www
    -0.10
    =ax
    -0.10
    onda
    -0.09
    Č↵
    -0.09
     fon
    -0.09
    ă
    -0.09
     Mutable
    -0.09
    .linkedin
    -0.09
     dow
    -0.09
    POSITIVE LOGITS
     typically
    0.09
     crossword
    0.08
    ersh
    0.08
    tod
    0.08
     virtually
    0.08
     dating
    0.08
    lush
    0.08
     vs
    0.08
    <br
    0.07
     VS
    0.07
    Activations Density 2.291%

    No Known Activations