© 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. 112882
    Prev
    Next
    INDEX
    Explanations

    offer and acceptance

    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
    .partial
    -0.08
     meaningless
    -0.08
    moil
    -0.08
     Opport
    -0.08
    quential
    -0.07
    .logout
    -0.07
    /per
    -0.07
    OC
    -0.07
    818
    -0.07
    ingle
    -0.07
    POSITIVE LOGITS
     accepted
    0.31
     acceptance
    0.29
     Accepted
    0.28
     ACCEPT
    0.27
    accepted
    0.25
     accept
    0.25
    Accepted
    0.25
    accept
    0.24
     candidacy
    0.24
     Accept
    0.24
    Activations Density 1.003%

    No Known Activations