© 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. 4787
    Prev
    Next
    INDEX
    Explanations

    contrast conjunctions

    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
     thus
    -0.15
    thus
    -0.12
    hsi
    -0.10
     sorte
    -0.10
    —for
    -0.10
     Pur
    -0.10
    ENO
    -0.10
     CCC
    -0.09
    ;/*
    -0.09
    Thus
    -0.09
    POSITIVE LOGITS
     However
    0.15
     however
    0.15
    However
    0.13
     unl
    0.13
     Unfortunately
    0.13
    however
    0.13
     later
    0.13
     unfortunately
    0.13
     Nevertheless
    0.12
     unfortunate
    0.12
    Activations Density 0.213%

    No Known Activations