© 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. 111713
    Prev
    Next
    INDEX
    Explanations

    standards and requirements

    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
    iei
    -0.10
    imits
    -0.09
     guideline
    -0.09
    icals
    -0.09
     ASTM
    -0.09
     Specification
    -0.09
    alar
    -0.09
    ikh
    -0.09
     Hubb
    -0.09
     blackout
    -0.09
    POSITIVE LOGITS
     cast
    0.12
     Hod
    0.10
     Cast
    0.10
     requis
    0.09
     condemned
    0.09
     condem
    0.09
     judging
    0.08
     Moy
    0.08
    uy
    0.08
     hail
    0.08
    Activations Density 0.004%

    No Known Activations