© 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. 28301
    Prev
    Next
    INDEX
    Explanations

    more than

    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
     three
    -0.09
     acceptable
    -0.08
     five
    -0.08
     seven
    -0.08
     ju
    -0.08
     prer
    -0.08
     four
    -0.08
     represent
    -0.07
     two
    -0.07
     Mak
    -0.07
    POSITIVE LOGITS
     countless
    0.20
     numerous
    0.16
     enumerable
    0.15
     count
    0.15
     enumerate
    0.15
    -count
    0.15
     Count
    0.14
    .count
    0.14
    count
    0.14
     Numerous
    0.13
    Activations Density 0.005%

    No Known Activations