© 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. 4801
    Prev
    Next
    INDEX
    Explanations

    compelling nouns

    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
     gladly
    -0.15
     eagerly
    -0.14
     recl
    -0.13
     brav
    -0.13
     voluntarily
    -0.13
     willingly
    -0.12
     appealed
    -0.12
     grate
    -0.12
     shy
    -0.11
     recip
    -0.11
    POSITIVE LOGITS
     forcing
    0.19
     forcibly
    0.18
    forcing
    0.17
     forcefully
    0.16
     punishment
    0.15
     humiliating
    0.14
     humiliation
    0.14
     punitive
    0.14
     punish
    0.13
     force
    0.13
    Activations Density 0.019%

    No Known Activations