© 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. 25041
    Prev
    Next
    INDEX
    Explanations

    unless, except, without, outside

    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
    abei
    -0.09
     ClassName
    -0.09
    +_
    -0.08
    -May
    -0.08
     Kai
    -0.08
     specialized
    -0.08
    cest
    -0.08
    +c
    -0.08
    amental
    -0.08
    (equal
    -0.08
    POSITIVE LOGITS
     unless
    0.29
    unless
    0.21
     anything
    0.21
     Unless
    0.19
     except
    0.19
     without
    0.17
     Anything
    0.17
     incomplete
    0.17
     outside
    0.17
    Unless
    0.17
    Activations Density 0.417%

    No Known Activations