© 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. 29730
    Prev
    Next
    INDEX
    Explanations

    to be or become something better

    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
    rary
    -0.11
    peg
    -0.10
     pf
    -0.10
     displaced
    -0.10
     obligation
    -0.10
    442
    -0.10
    angered
    -0.10
    interactive
    -0.10
    pf
    -0.10
     neglected
    -0.10
    POSITIVE LOGITS
     better
    0.16
     smarter
    0.15
     taller
    0.14
     successful
    0.13
     healthier
    0.13
     stronger
    0.12
    better
    0.12
     masters
    0.12
     closer
    0.12
     accepted
    0.12
    Activations Density 0.051%

    No Known Activations