© 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. 18767
    Prev
    Next
    INDEX
    Explanations

    waves and action

    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
    asha
    -0.11
    /we
    -0.10
     Schultz
    -0.10
    ander
    -0.10
    urg
    -0.10
     targ
    -0.10
    âĢİ
    -0.10
    iran
    -0.09
    liv
    -0.09
    unter
    -0.09
    POSITIVE LOGITS
     crashing
    0.16
     waves
    0.15
    front
    0.14
    forms
    0.13
     Waves
    0.13
    -like
    0.12
     goodbye
    0.12
    LENGTH
    0.12
    guide
    0.11
     hitting
    0.11
    Activations Density 0.014%

    No Known Activations