© 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. 49351
    Prev
    Next
    INDEX
    Explanations

    spraying, spray, sprays

    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
    okin
    -0.10
     scripted
    -0.09
    oning
    -0.09
     crush
    -0.09
    ppo
    -0.09
     TORT
    -0.09
     stacking
    -0.09
     Trem
    -0.09
     smear
    -0.09
    stk
    -0.09
    POSITIVE LOGITS
    Spr
    0.14
     aeros
    0.13
     spray
    0.13
     Spr
    0.12
    spr
    0.12
     Spray
    0.12
     spr
    0.12
     onto
    0.11
     fung
    0.11
     disin
    0.11
    Activations Density 0.021%

    No Known Activations