© 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. 30200
    Prev
    Next
    INDEX
    Explanations

    words ending in 'ies' or 'ries'

    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
    vey
    -0.09
    uppe
    -0.08
    SG
    -0.08
    лÑĮÑĤ
    -0.08
    alien
    -0.08
    avad
    -0.08
    ipsis
    -0.08
    ropy
    -0.08
    ishi
    -0.07
     dimensional
    -0.07
    POSITIVE LOGITS
    enis
    0.13
     Racing
    0.12
    ties
    0.11
    lab
    0.11
    eco
    0.11
    eg
    0.10
    dens
    0.10
    eler
    0.10
     climb
    0.10
     RUNNING
    0.10
    Activations Density 0.017%

    No Known Activations