© 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. 112619
    Prev
    Next
    INDEX
    Explanations

    verbs of action or influence

    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
    obel
    -0.12
    emit
    -0.11
     enactment
    -0.10
    jon
    -0.10
     undergoing
    -0.10
    agar
    -0.10
    buch
    -0.10
     dropping
    -0.10
    loc
    -0.09
    locs
    -0.09
    POSITIVE LOGITS
     enlight
    0.12
     energ
    0.12
     empower
    0.12
     deceive
    0.12
     nour
    0.12
     Energ
    0.11
     traumat
    0.11
     interrog
    0.10
     protects
    0.10
     infect
    0.10
    Activations Density 0.180%

    No Known Activations