© 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. 117217
    Prev
    Next
    INDEX
    Explanations

    "so", "that's"

    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
     surely
    -0.10
    éĽħ
    -0.10
     exactly
    -0.10
     Hop
    -0.10
    æľ¬
    -0.09
     mos
    -0.09
    sure
    -0.09
     duty
    -0.09
     Hal
    -0.09
     Mos
    -0.09
    POSITIVE LOGITS
     THAT
    0.12
     finally
    0.10
     Sick
    0.09
    hoot
    0.09
    (that
    0.09
     Solic
    0.09
    finally
    0.08
    cil
    0.08
     Occup
    0.08
    reon
    0.08
    Activations Density 0.038%

    No Known Activations