© 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. 14108
    Prev
    Next
    INDEX
    Explanations

    firsthand experience or observation

    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
    oret
    -0.10
     unknown
    -0.09
    ®
    -0.09
    ild
    -0.09
     somehow
    -0.09
    pth
    -0.08
     theoretically
    -0.08
     availability
    -0.08
    ody
    -0.08
    GOR
    -0.08
    POSITIVE LOGITS
     firsthand
    0.13
     practically
    0.13
     witnessed
    0.12
     saw
    0.12
     seen
    0.12
     eyewitness
    0.11
     watched
    0.11
     heard
    0.11
    Checked
    0.10
    peek
    0.10
    Activations Density 0.052%

    No Known Activations