© 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. 49414
    Prev
    Next
    INDEX
    Explanations

    checks if something is

    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
    chw
    -0.10
     sure
    -0.09
     tempted
    -0.09
     sincer
    -0.09
     unstoppable
    -0.09
    -IS
    -0.09
     glad
    -0.09
    otto
    -0.09
     surpr
    -0.09
     careful
    -0.09
    POSITIVE LOGITS
    /is
    0.12
     part
    0.12
     actively
    0.12
     involved
    0.11
     utilizing
    0.11
     acting
    0.11
     exhibiting
    0.11
     causing
    0.11
     behaving
    0.11
     active
    0.10
    Activations Density 0.132%

    No Known Activations