© 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. 91782
    Prev
    Next
    INDEX
    Explanations

    inter- words: intercourse, intergroup, intercultural, intercalated, intercellular

    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
    encial
    -0.13
    ega
    -0.12
    e
    -0.11
     pin
    -0.11
    oshi
    -0.10
    amins
    -0.10
     booking
    -0.10
     subtle
    -0.10
     Pin
    -0.10
    ed
    -0.10
    POSITIVE LOGITS
    onso
    0.10
    s
    0.09
    ourse
    0.09
    oft
    0.09
    baugh
    0.08
    uzzle
    0.08
    fal
    0.08
    æģ¯
    0.08
    ordinate
    0.07
     ages
    0.07
    Activations Density 0.008%

    No Known Activations