© 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. 46284
    Prev
    Next
    INDEX
    Explanations

    anyway or unlikely

    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
     frustrating
    -0.10
     nag
    -0.10
     definite
    -0.09
     unresolved
    -0.09
    .#
    -0.09
    YES
    -0.08
     Unexpected
    -0.08
     GENERIC
    -0.08
     Quar
    -0.08
     Nigel
    -0.08
    POSITIVE LOGITS
     anyway
    0.23
     anyways
    0.22
     anyhow
    0.20
     wouldn
    0.19
     Anyway
    0.17
     unnecessary
    0.16
    Anyway
    0.16
     unlikely
    0.16
     irrelevant
    0.14
     hardly
    0.13
    Activations Density 0.079%

    No Known Activations