© 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. 4473
    Prev
    Next
    INDEX
    Explanations

    have/has/had + past participle

    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
    ante
    -0.09
     Playground
    -0.09
    ober
    -0.09
     Sheldon
    -0.09
     circles
    -0.09
    roc
    -0.09
     captions
    -0.08
    LEASE
    -0.08
    ayo
    -0.08
     saat
    -0.08
    POSITIVE LOGITS
     rehe
    0.16
     frequently
    0.13
     never
    0.12
     done
    0.11
    bart
    0.10
     rehearsal
    0.10
     frequ
    0.10
     pil
    0.10
     rehears
    0.10
    nger
    0.10
    Activations Density 0.106%

    No Known Activations