© 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. 114807
    Prev
    Next
    INDEX
    Explanations

    part of words ending in -aster, -endra, -uk, -our

    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
    ble
    -0.11
    mer
    -0.11
    i
    -0.10
    ad
    -0.10
    inati
    -0.10
     breakdown
    -0.10
    oris
    -0.10
    b
    -0.09
    h
    -0.09
    el
    -0.09
    POSITIVE LOGITS
     Impress
    0.16
    rese
    0.12
    edian
    0.12
    leness
    0.12
    strup
    0.11
    ridged
    0.11
    erce
    0.10
    esity
    0.10
     impress
    0.10
     taboo
    0.10
    Activations Density 0.030%

    No Known Activations