© 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. 87931
    Prev
    Next
    INDEX
    Explanations

    and, without, or

    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
     angst
    -0.15
     distra
    -0.13
     emotional
    -0.13
     Psychological
    -0.13
     panicked
    -0.12
     anxiety
    -0.12
     Relax
    -0.12
     emotions
    -0.11
     discomfort
    -0.11
     uncomfortable
    -0.11
    POSITIVE LOGITS
     blaming
    0.11
    ewe
    0.11
     lash
    0.11
    ksam
    0.10
     beauty
    0.10
     blame
    0.10
     shaved
    0.10
     censor
    0.10
     Tent
    0.09
     Ruf
    0.09
    Activations Density 0.346%

    No Known Activations