© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 45969
    Prev
    Next
    INDEX
    Explanations

    two, followed by an adjective

    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
    Negative Logits
     Fancy
    -0.09
    onz
    -0.09
    Getty
    -0.08
    [,]
    -0.08
    -minded
    -0.08
    /ex
    -0.08
    amarin
    -0.08
    usto
    -0.08
    aed
    -0.08
    leshoot
    -0.08
    POSITIVE LOGITS
     admittedly
    0.13
     comparatively
    0.13
     frankly
    0.12
     seemingly
    0.12
     relatively
    0.11
     pardon
    0.11
     slightly
    0.11
     presumed
    0.11
    eland
    0.11
     ah
    0.11
    Activations Density 0.092%

    No Known Activations