© 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. 117373
    Prev
    Next
    INDEX
    Explanations

    fitting and appropriate

    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
    228
    -0.10
    219
    -0.10
    noch
    -0.10
    acie
    -0.10
     pes
    -0.10
    tog
    -0.09
    >(*
    -0.09
    QUAL
    -0.09
     Compact
    -0.09
    orian
    -0.09
    POSITIVE LOGITS
     fitting
    0.66
     apt
    0.56
     appropriate
    0.56
     appropriately
    0.55
    appropriate
    0.43
     Appropri
    0.40
     Apt
    0.39
    appropri
    0.38
     appropri
    0.38
    fit
    0.35
    Activations Density 0.345%

    No Known Activations