© 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. 26569
    Prev
    Next
    INDEX
    Explanations

    deal with a situation

    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
     bou
    -0.10
     itself
    -0.09
     Norm
    -0.09
     proceeding
    -0.09
     Incre
    -0.09
     altogether
    -0.09
    &S
    -0.09
    Nib
    -0.09
    uing
    -0.09
     unmist
    -0.09
    POSITIVE LOGITS
    774
    0.10
    iegel
    0.09
    344
    0.09
    iggins
    0.09
    497
    0.09
     lest
    0.09
    agan
    0.08
    ices
    0.08
    772
    0.08
    ively
    0.08
    Activations Density 1.700%

    No Known Activations