© 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. 24958
    Prev
    Next
    INDEX
    Explanations

    signing agreements and consent

    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
     signatures
    -0.16
     signed
    -0.16
     signature
    -0.13
    signed
    -0.12
     Signature
    -0.11
    _signature
    -0.11
     Signed
    -0.11
    -signed
    -0.10
    ajas
    -0.10
     badges
    -0.10
    POSITIVE LOGITS
     acknowledging
    0.13
     relinqu
    0.11
     appropri
    0.10
     admitting
    0.10
    Decl
    0.09
     inher
    0.09
     accepting
    0.09
     stating
    0.09
     illeg
    0.09
     required
    0.09
    Activations Density 0.041%

    No Known Activations