© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 7598
    Prev
    Next
    INDEX
    Explanations

    valuation, object, judges, assign

    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
     brib
    -0.11
     refunded
    -0.11
     corrected
    -0.10
     Correction
    -0.10
    contra
    -0.09
     correction
    -0.09
     ostensibly
    -0.09
     corrections
    -0.09
     brav
    -0.09
     Corrections
    -0.09
    POSITIVE LOGITS
     assigning
    0.20
     dep
    0.19
     commod
    0.19
     treating
    0.18
     idol
    0.18
     object
    0.17
     fetish
    0.17
     depreciation
    0.16
     exagger
    0.16
     assign
    0.16
    Activations Density 0.229%

    No Known Activations