© 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. 89374
    Prev
    Next
    INDEX
    Explanations

    error or syntax issue

    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
    /op
    -0.10
     perf
    -0.09
    730
    -0.09
     trab
    -0.09
     pile
    -0.09
     Anast
    -0.09
    ì²´
    -0.08
     claimed
    -0.08
    aks
    -0.08
     oss
    -0.08
    POSITIVE LOGITS
     embarrassing
    0.14
     lint
    0.13
     embar
    0.13
     embarrass
    0.13
     invisible
    0.12
     typo
    0.12
     unaware
    0.12
     tails
    0.12
    Aware
    0.12
     snag
    0.12
    Activations Density 0.042%

    No Known Activations