© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27679
    Prev
    Next
    INDEX
    Explanations

    end of something

    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
    lama
    -0.11
     interv
    -0.10
    -minded
    -0.09
    ened
    -0.09
    arc
    -0.09
    makers
    -0.09
     sided
    -0.09
     minded
    -0.09
    unting
    -0.09
    atore
    -0.09
    POSITIVE LOGITS
     nearest
    0.11
     toe
    0.11
     Sass
    0.10
    -round
    0.10
     boot
    0.09
    /boot
    0.09
     tail
    0.09
     closest
    0.09
    tail
    0.09
     boots
    0.09
    Activations Density 0.028%

    No Known Activations