© 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. 92586
    Prev
    Next
    INDEX
    Explanations

    neither nor why

    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
    ithe
    -0.10
     Hanna
    -0.09
    uf
    -0.09
     Instead
    -0.09
    umi
    -0.09
    acom
    -0.09
     definite
    -0.08
    Ñħодим
    -0.08
     everyone
    -0.08
     preferable
    -0.08
    POSITIVE LOGITS
     neither
    0.27
     Neither
    0.22
    Neither
    0.21
     why
    0.16
     nor
    0.15
    why
    0.13
    Nor
    0.12
    ne
    0.12
     Why
    0.12
     likewise
    0.12
    Activations Density 0.059%

    No Known Activations