© 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. 46174
    Prev
    Next
    INDEX
    Explanations

    on/off states

    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
    ODO
    -0.13
    orrent
    -0.11
     outr
    -0.11
    ucker
    -0.10
     forc
    -0.10
    ECH
    -0.10
    booking
    -0.10
    iser
    -0.10
    urer
    -0.10
     whence
    -0.10
    POSITIVE LOGITS
    /off
    0.14
     enough
    0.09
    ames
    0.09
     tether
    0.09
    /power
    0.09
     Savage
    0.09
    enes
    0.08
    zc
    0.08
     buzz
    0.08
    osh
    0.08
    Activations Density 0.002%

    No Known Activations