© 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. 6614
    Prev
    Next
    INDEX
    Explanations

    and rewarding, specialized, events, blog

    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
     flora
    -0.11
    abile
    -0.11
     calmly
    -0.10
     pard
    -0.10
     timed
    -0.10
    529
    -0.10
    efa
    -0.10
    wan
    -0.10
    572
    -0.09
    physical
    -0.09
    POSITIVE LOGITS
     camar
    0.09
     exclus
    0.09
     nostalgia
    0.08
     extravag
    0.08
     intrigue
    0.08
     indulge
    0.08
     discretion
    0.08
     indul
    0.07
     Robbie
    0.07
     Higgins
    0.07
    Activations Density 0.066%

    No Known Activations