© 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. 7063
    Prev
    Next
    INDEX
    Explanations

    fan of / not a fan of

    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
    iesel
    -0.11
    annot
    -0.09
    glas
    -0.08
    Young
    -0.08
    rey
    -0.08
    lasting
    -0.08
    ies
    -0.08
    712
    -0.08
     Young
    -0.08
     dared
    -0.08
    POSITIVE LOGITS
     prospects
    0.13
     idea
    0.12
     prospect
    0.12
    idea
    0.10
     Reeves
    0.10
    Newsletter
    0.10
     revelations
    0.10
     prolong
    0.10
    861
    0.10
     Idea
    0.10
    Activations Density 0.014%

    No Known Activations