© 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. 50539
    Prev
    Next
    INDEX
    Explanations

    agree/disagree

    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
    alian
    -0.12
    idth
    -0.11
    clare
    -0.11
     considerations
    -0.11
    umas
    -0.11
    aley
    -0.10
    ALER
    -0.10
     courtesy
    -0.10
    enty
    -0.10
    Joined
    -0.10
    POSITIVE LOGITS
     disagree
    0.11
     unanimously
    0.11
     reluctantly
    0.10
     beforehand
    0.09
    agree
    0.09
     disagrees
    0.09
    /ag
    0.09
     enthusiastically
    0.09
     agree
    0.09
     terms
    0.09
    Activations Density 0.121%

    No Known Activations