© 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. 30829
    Prev
    Next
    INDEX
    Explanations

    completing or hastening actions

    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
     IM
    -0.11
     towel
    -0.10
    cloth
    -0.09
    Holder
    -0.09
    psc
    -0.08
     Hold
    -0.08
    213
    -0.08
     Roose
    -0.08
     compliments
    -0.08
    capture
    -0.08
    POSITIVE LOGITS
     altogether
    0.13
     hastily
    0.13
     entirely
    0.12
     completely
    0.12
     frantic
    0.12
     hurried
    0.12
     quickest
    0.12
     quickly
    0.12
     swiftly
    0.11
     COMPLETE
    0.11
    Activations Density 0.017%

    No Known Activations