© 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. 25119
    Prev
    Next
    INDEX
    Explanations

    force yourself

    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
    Negative Logits
    udi
    -0.09
     asi
    -0.09
     discreet
    -0.09
     frankly
    -0.08
     incons
    -0.08
     unsub
    -0.08
    823
    -0.08
     vaguely
    -0.08
    undi
    -0.08
     rever
    -0.08
    POSITIVE LOGITS
     calm
    0.14
     focus
    0.13
     breathing
    0.13
    stay
    0.12
     breathe
    0.12
     clam
    0.11
    [c
    0.11
     Focus
    0.11
     steel
    0.11
    Focus
    0.11
    Activations Density 0.011%

    No Known Activations