© 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. 29525
    Prev
    Next
    INDEX
    Explanations

    any more / any time / any way

    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
    atr
    -0.11
     ,,
    -0.10
     administr
    -0.09
    eln
    -0.09
    aire
    -0.09
     #↵↵
    -0.09
    .sg
    -0.09
    .biz
    -0.09
    ius
    -0.09
    ambre
    -0.09
    POSITIVE LOGITS
    tone
    0.11
     longer
    0.11
     day
    0.10
    times
    0.10
    day
    0.10
    /or
    0.09
    ways
    0.09
    isser
    0.09
     nowhere
    0.09
    hw
    0.09
    Activations Density 0.017%

    No Known Activations