© 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. 25226
    Prev
    Next
    INDEX
    Explanations

    pretty much

    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
     very
    -0.08
    inet
    -0.08
    kers
    -0.07
    ic
    -0.07
    st
    -0.07
    IPC
    -0.07
    re
    -0.07
    res
    -0.07
     immortal
    -0.06
    ion
    -0.06
    POSITIVE LOGITS
     much
    0.13
     Polly
    0.13
     soon
    0.13
    -boy
    0.12
    inp
    0.12
    -print
    0.12
     Peb
    0.12
    ANY
    0.12
     sure
    0.12
     MUCH
    0.12
    Activations Density 0.011%

    No Known Activations