© 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. 33897
    Prev
    Next
    INDEX
    Explanations

    contrastive conjunctions

    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
    CM
    -0.10
    alten
    -0.10
     Thumb
    -0.09
    (___
    -0.09
     Prest
    -0.09
     WTF
    -0.09
    fusion
    -0.09
    ADO
    -0.09
    feld
    -0.09
    âĢ¦"↵↵
    -0.08
    POSITIVE LOGITS
     gearing
    0.09
    /Library
    0.08
    iga
    0.08
    lay
    0.08
     COMPLETE
    0.08
    keley
    0.08
     Hut
    0.08
     doll
    0.08
     Muk
    0.08
    -uri
    0.08
    Activations Density 0.075%

    No Known Activations