© 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. 91591
    Prev
    Next
    INDEX
    Explanations

    doesn't mean it

    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
     bre
    -0.09
     means
    -0.09
     Jenna
    -0.09
    sure
    -0.09
     Tub
    -0.08
    acco
    -0.08
     purely
    -0.08
    chte
    -0.08
     hus
    -0.08
     Hor
    -0.08
    POSITIVE LOGITS
     deserve
    0.10
     necessarily
    0.10
    ucher
    0.09
    /Common
    0.09
     anything
    0.09
     Bere
    0.09
    WC
    0.09
    PERT
    0.09
     Cout
    0.09
    stop
    0.09
    Activations Density 0.006%

    No Known Activations