© 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. 87949
    Prev
    Next
    INDEX
    Explanations

    self "I" or "we" followed by state/intention

    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
    aug
    -0.09
    arin
    -0.09
    lab
    -0.09
    abl
    -0.08
     armor
    -0.08
    aupt
    -0.08
     evidently
    -0.08
     directional
    -0.08
     Harden
    -0.08
     elig
    -0.08
    POSITIVE LOGITS
     advise
    0.12
     WARN
    0.12
     wonder
    0.11
     warn
    0.11
     advice
    0.11
    ichen
    0.11
    cy
    0.10
    gd
    0.10
    otos
    0.10
    bab
    0.10
    Activations Density 0.011%

    No Known Activations