© 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. 87965
    Prev
    Next
    INDEX
    Explanations

    end-use value

    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
     mine
    -0.10
     undergo
    -0.10
     Kelley
    -0.10
     paras
    -0.10
     spontaneously
    -0.10
    blas
    -0.09
     symb
    -0.09
     weakness
    -0.09
    isti
    -0.09
    inel
    -0.09
    POSITIVE LOGITS
     afterward
    0.12
     satisfactory
    0.11
     satisfied
    0.11
     satisfaction
    0.10
     hopes
    0.10
     satisfying
    0.10
     eventually
    0.10
     Message
    0.10
     regret
    0.10
     ÑģообÑī
    0.10
    Activations Density 0.006%

    No Known Activations