© 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. 50052
    Prev
    Next
    INDEX
    Explanations

    agreement, deal, agent, network

    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
     oraz
    -0.12
     Rather
    -0.10
    icker
    -0.10
     rather
    -0.10
     Booth
    -0.10
     ainsi
    -0.09
     både
    -0.09
    —not
    -0.09
     however
    -0.09
    Rather
    -0.09
    POSITIVE LOGITS
     altogether
    0.19
     outright
    0.17
     thereof
    0.13
     whichever
    0.13
     depending
    0.12
     somehow
    0.10
     Sa
    0.10
     elsewhere
    0.10
    /
    0.09
     Ou
    0.09
    Activations Density 0.690%

    No Known Activations