© 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. 28313
    Prev
    Next
    INDEX
    Explanations

    return or arrive back home

    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
    ieres
    -0.11
    -clear
    -0.09
     Fare
    -0.09
     goodbye
    -0.09
     sucker
    -0.09
    orque
    -0.09
     Cort
    -0.09
     capac
    -0.09
     Fresno
    -0.09
     bulld
    -0.09
    POSITIVE LOGITS
     exhausted
    0.25
     battered
    0.18
     returning
    0.17
     Exhaust
    0.17
     exhaustion
    0.17
     returned
    0.17
     bru
    0.16
     arrive
    0.16
     return
    0.16
     wounded
    0.16
    Activations Density 0.224%

    No Known Activations