© 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. 4664
    Prev
    Next
    INDEX
    Explanations

    leading to insertion

    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
     coco
    -0.10
     Wien
    -0.10
    queda
    -0.09
    rita
    -0.09
     dissolved
    -0.09
    Gate
    -0.09
    xit
    -0.09
     Civ
    -0.09
     Kenn
    -0.09
     Visibility
    -0.09
    POSITIVE LOGITS
     ring
    0.11
     inverted
    0.11
     correct
    0.10
    haled
    0.10
     pinch
    0.10
    hang
    0.10
    itational
    0.09
     unfolding
    0.09
     Arrow
    0.09
    -ring
    0.09
    Activations Density 0.076%

    No Known Activations