© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 89663
    Prev
    Next
    INDEX
    Explanations

    everything you need

    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
    idel
    -0.12
     Jennings
    -0.11
    achte
    -0.10
    azzi
    -0.10
    /MPL
    -0.10
    aga
    -0.10
    kov
    -0.09
     ineligible
    -0.09
    vn
    -0.09
     coded
    -0.09
    POSITIVE LOGITS
     necessary
    0.42
     needed
    0.38
    necessary
    0.30
     Necessary
    0.29
     required
    0.29
    needed
    0.28
     Needed
    0.27
     necessities
    0.27
     essentials
    0.26
     requisite
    0.26
    Activations Density 0.247%

    No Known Activations