© 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. 47817
    Prev
    Next
    INDEX
    Explanations

    some qualities are better than others

    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
     Cre
    -0.10
     Franken
    -0.10
     Camden
    -0.10
     Lowest
    -0.10
     Cru
    -0.10
     zab
    -0.09
    321
    -0.09
    lei
    -0.09
     Weaver
    -0.09
     Meadow
    -0.09
    POSITIVE LOGITS
     more
    0.24
     better
    0.23
     than
    0.20
     stronger
    0.19
     louder
    0.19
     harder
    0.19
     worse
    0.19
    better
    0.17
     easier
    0.17
     richer
    0.17
    Activations Density 0.105%

    No Known Activations