© 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. 115722
    Prev
    Next
    INDEX
    Explanations

    own to match your decor

    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
     susp
    -0.12
     thrust
    -0.10
     informal
    -0.09
     Clement
    -0.09
    ä¼
    -0.09
     mir
    -0.08
     Lunch
    -0.08
     simul
    -0.08
     tack
    -0.08
     damp
    -0.08
    POSITIVE LOGITS
     Spar
    0.10
    abies
    0.10
     Serg
    0.09
    autos
    0.09
     substitute
    0.09
    fre
    0.09
    aea
    0.09
    kee
    0.09
     fle
    0.09
    OTS
    0.09
    Activations Density 0.002%

    No Known Activations