© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115469
    Prev
    Next
    INDEX
    Explanations

    affects somebody or happens to someone

    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
    bows
    -0.10
    elist
    -0.10
     Bare
    -0.10
     Anast
    -0.10
     Barnes
    -0.09
     Gro
    -0.09
     Opr
    -0.09
     delights
    -0.09
     Noah
    -0.09
     discour
    -0.09
    POSITIVE LOGITS
     happening
    0.16
     personally
    0.16
     applicable
    0.15
     applies
    0.14
     apply
    0.14
     applied
    0.14
     happen
    0.14
     affecting
    0.14
     Happ
    0.12
     somebody
    0.12
    Activations Density 0.109%

    No Known Activations