© 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. 92384
    Prev
    Next
    INDEX
    Explanations

    instead of

    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
     unlike
    -0.08
     Wanted
    -0.07
     due
    -0.07
     wanted
    -0.07
     potentially
    -0.07
     amidst
    -0.07
     intrinsic
    -0.07
     Vic
    -0.07
     wanna
    -0.07
     optional
    -0.07
    POSITIVE LOGITS
     instead
    0.24
    instead
    0.21
     suffice
    0.20
    Instead
    0.17
     until
    0.17
    until
    0.16
     Instead
    0.16
     luckily
    0.16
    Fortunately
    0.16
     Luckily
    0.16
    Activations Density 0.515%

    No Known Activations