© 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. 46744
    Prev
    Next
    INDEX
    Explanations

    fairness and shine

    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
     ance
    -0.10
     assass
    -0.10
     host
    -0.10
     subordinate
    -0.10
     annihil
    -0.10
     Ga
    -0.10
    Ga
    -0.10
    killer
    -0.09
     trail
    -0.09
     damn
    -0.09
    POSITIVE LOGITS
     faire
    0.12
     shiny
    0.10
     fair
    0.10
     fairness
    0.10
     schn
    0.09
     shimmer
    0.09
     Tits
    0.09
    owy
    0.09
     pea
    0.09
     blah
    0.09
    Activations Density 0.008%

    No Known Activations