© 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. 4561
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunctions like but

    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
     tonight
    -0.16
     currently
    -0.14
     herein
    -0.12
     tomorrow
    -0.12
     now
    -0.12
     today
    -0.11
    currently
    -0.11
     Tonight
    -0.11
    Currently
    -0.11
     hereby
    -0.10
    POSITIVE LOGITS
    ..."↵↵
    0.19
     ..."↵↵
    0.17
    âĢ¦”↵↵
    0.17
     sort
    0.17
    ..."↵
    0.17
    âĢ¦"↵↵
    0.15
     Afterwards
    0.13
     kinda
    0.13
    [,]
    0.13
     [,
    0.13
    Activations Density 0.041%

    No Known Activations