© 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. 14598
    Prev
    Next
    INDEX
    Explanations

    check verbs

    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
     NotImplemented
    -0.12
     subdued
    -0.11
     invitations
    -0.10
     hints
    -0.10
     autoplay
    -0.10
     tempered
    -0.10
    _highlight
    -0.09
     intriguing
    -0.09
     implic
    -0.09
    atto
    -0.09
    POSITIVE LOGITS
     checking
    0.60
     Checking
    0.54
     checks
    0.52
     check
    0.52
    Checking
    0.50
    checking
    0.48
     verifying
    0.48
    -check
    0.47
     checked
    0.47
     пÑĢовеÑĢ
    0.47
    Activations Density 1.336%

    No Known Activations