© 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. 13982
    Prev
    Next
    INDEX
    Explanations

    can't help but

    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
     hopefully
    -0.11
     presumably
    -0.11
     thankfully
    -0.10
    ilm
    -0.10
     undecided
    -0.09
    undle
    -0.09
     unsure
    -0.08
     Hind
    -0.08
     never
    -0.08
     iterators
    -0.08
    POSITIVE LOGITS
     nor
    0.29
     Nor
    0.22
    nor
    0.20
     anymore
    0.19
    Nor
    0.18
     NOR
    0.12
    anni
    0.11
    —even
    0.11
    ingt
    0.11
     Especially
    0.10
    Activations Density 0.096%

    No Known Activations