© 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. 18399
    Prev
    Next
    INDEX
    Explanations

    descriptive positive words

    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
    vero
    -0.09
    IFn
    -0.09
    orde
    -0.08
     clich
    -0.08
     Nay
    -0.08
     prostitut
    -0.08
    mpz
    -0.08
    ihu
    -0.08
     immedi
    -0.08
     Interracial
    -0.08
    POSITIVE LOGITS
     wonderful
    0.52
     beautiful
    0.47
     lovely
    0.46
     wonderfully
    0.45
     excellent
    0.45
     amazing
    0.45
     delightful
    0.45
     awesome
    0.44
     magnificent
    0.43
     brilliant
    0.43
    Activations Density 0.723%

    No Known Activations