© 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. 29444
    Prev
    Next
    INDEX
    Explanations

    license terms and conditions

    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
     maxi
    -0.10
     hire
    -0.10
     mini
    -0.10
     Cath
    -0.10
     Alexandra
    -0.09
     furnish
    -0.09
    hire
    -0.09
     Strand
    -0.09
     «
    -0.09
     located
    -0.09
    POSITIVE LOGITS
    (...)
    0.10
    kov
    0.08
    iskey
    0.08
    bek
    0.08
    /perl
    0.08
    bef
    0.08
     superf
    0.08
     reb
    0.08
    agli
    0.08
    elow
    0.08
    Activations Density 0.001%

    No Known Activations