© 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. 7978
    Prev
    Next
    INDEX
    Explanations

    parenthetical information or academic context

    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
    (or
    -0.14
    —or
    -0.12
    *)
    -0.11
    ',)↵
    -0.11
    (and
    -0.10
    —including
    -0.10
    (with
    -0.10
    -ish
    -0.10
    (not
    -0.09
    —even
    -0.09
    POSITIVE LOGITS
     (
    0.27
    ãĢĤ(
    0.27
     }(
    0.27
     ([
    0.25
     (**
    0.25
     ()↵
    0.24
     )(
    0.24
     ()↵↵
    0.24
    ...(
    0.24
     ().
    0.24
    Activations Density 4.665%

    No Known Activations