© 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. 15115
    Prev
    Next
    INDEX
    Explanations

    accept that/of

    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
     manners
    -0.10
     contours
    -0.09
     Krak
    -0.09
     genom
    -0.09
     unb
    -0.09
     tribute
    -0.09
    umer
    -0.09
    ije
    -0.09
     distinctly
    -0.09
     anywhere
    -0.09
    POSITIVE LOGITS
     acceptance
    0.23
     accepting
    0.22
     accept
    0.21
     Accept
    0.20
     accepted
    0.20
    accept
    0.20
     accepts
    0.19
     ACCEPT
    0.19
    Accept
    0.19
    accepted
    0.17
    Activations Density 0.017%

    No Known Activations