© 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. 32458
    Prev
    Next
    INDEX
    Explanations

    revel, relish, marvel

    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
    enson
    -0.13
    ynes
    -0.11
    atu
    -0.10
    ioni
    -0.10
     Worse
    -0.10
    LM
    -0.10
    unit
    -0.10
    izzo
    -0.10
    enn
    -0.09
    akh
    -0.09
    POSITIVE LOGITS
     in
    0.12
    inge
    0.09
    ing
    0.09
     revel
    0.09
    ously
    0.08
    inth
    0.08
     cac
    0.08
     opportunities
    0.08
    edin
    0.08
    æ±
    0.08
    Activations Density 0.003%

    No Known Activations