© 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. 14317
    Prev
    Next
    INDEX
    Explanations

    successes or failures

    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
     astonished
    -0.10
     extrad
    -0.10
     filmer
    -0.10
     perc
    -0.10
     hypnot
    -0.10
    pector
    -0.09
     whistle
    -0.09
     proport
    -0.09
     amused
    -0.09
     dared
    -0.09
    POSITIVE LOGITS
     lack
    0.22
     failed
    0.22
     fail
    0.21
     wrong
    0.21
     fails
    0.21
     insufficient
    0.20
     disappoint
    0.20
     lacks
    0.19
     invalid
    0.19
    失
    0.19
    Activations Density 3.633%

    No Known Activations