© 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. 116650
    Prev
    Next
    INDEX
    Explanations

    last thing or event

    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
     extinction
    -0.10
    isser
    -0.10
     Josef
    -0.09
    ;break
    -0.09
    lemn
    -0.09
    isu
    -0.09
    lege
    -0.08
    riba
    -0.08
     numbering
    -0.08
    lush
    -0.08
    POSITIVE LOGITS
     remaining
    0.19
     vest
    0.18
    -ever
    0.15
     few
    0.15
    remaining
    0.14
     ounce
    0.14
     of
    0.13
     Remaining
    0.13
     possible
    0.13
     Vest
    0.13
    Activations Density 0.026%

    No Known Activations