© 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. 46877
    Prev
    Next
    INDEX
    Explanations

    resultative 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
    aus
    -0.10
    082
    -0.08
    обÑī
    -0.08
     çok
    -0.08
    thr
    -0.07
     dern
    -0.07
    otomy
    -0.07
    azo
    -0.07
    ewn
    -0.07
    olith
    -0.07
    POSITIVE LOGITS
     therefore
    0.75
     Therefore
    0.61
    Therefore
    0.59
     hence
    0.50
     thus
    0.50
     consequently
    0.46
     Hence
    0.45
     Thus
    0.43
     donc
    0.43
     accordingly
    0.42
    Activations Density 1.299%

    No Known Activations