© 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. 87905
    Prev
    Next
    INDEX
    Explanations

    simultaneously, alongside, opposite

    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
    Not in Any Lists

    No Comments

    Negative Logits
    cab
    -0.11
    andler
    -0.10
    æľ¬
    -0.10
    zk
    -0.09
     verz
    -0.09
    yi
    -0.09
    ISP
    -0.09
    adge
    -0.09
    atos
    -0.08
    arters
    -0.08
    POSITIVE LOGITS
     alongside
    0.18
     opposite
    0.16
     rival
    0.16
     simultaneously
    0.14
     matching
    0.13
     oppos
    0.12
     simult
    0.12
     recip
    0.12
     complementary
    0.12
     retal
    0.12
    Activations Density 0.194%

    No Known Activations