© 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. 49383
    Prev
    Next
    INDEX
    Explanations

    in or well

    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
    bane
    -0.10
     Edison
    -0.10
    heid
    -0.09
    assi
    -0.09
    dm
    -0.09
     quer
    -0.09
    lesh
    -0.09
     stuff
    -0.09
     Bog
    -0.09
    anship
    -0.09
    POSITIVE LOGITS
     perfectly
    0.20
     nicely
    0.15
     into
    0.14
     PERF
    0.14
     seamlessly
    0.14
     well
    0.14
     neatly
    0.13
    /work
    0.13
     snug
    0.13
     squarely
    0.12
    Activations Density 0.038%

    No Known Activations