© 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. 33937
    Prev
    Next
    INDEX
    Explanations

    adjectives for positive descriptions

    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
     kino
    -0.16
     implicitly
    -0.15
     fucked
    -0.14
    Whenever
    -0.14
     Kö
    -0.14
    fuck
    -0.14
     FUCK
    -0.14
     Fucked
    -0.14
     explicitly
    -0.14
     FAG
    -0.13
    POSITIVE LOGITS
     fabulous
    0.22
     hubby
    0.19
     mama
    0.14
     glean
    0.12
     yummy
    0.12
     lovely
    0.12
     xo
    0.11
     savvy
    0.11
     darn
    0.11
     fab
    0.10
    Activations Density 3.502%

    No Known Activations