© 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. 91275
    Prev
    Next
    INDEX
    Explanations

    rearing, reeling, raining, hauling, raking

    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
     mild
    -0.10
     wink
    -0.10
    mos
    -0.09
    flo
    -0.09
    artisan
    -0.08
     persuasion
    -0.08
     sheer
    -0.08
    bits
    -0.08
     outlining
    -0.08
     Highly
    -0.08
    POSITIVE LOGITS
    awy
    0.10
    STA
    0.10
     reco
    0.10
    952
    0.10
    cip
    0.10
     pis
    0.10
    ABCDE
    0.10
     lassen
    0.09
     backward
    0.09
    CTR
    0.09
    Activations Density 0.007%

    No Known Activations