© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27015
    Prev
    Next
    INDEX
    Explanations

    consequently, therefore, thus

    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
     therefore
    -0.20
     donc
    -0.14
     Therefore
    -0.13
    Therefore
    -0.13
     thus
    -0.13
     consequently
    -0.12
     accordingly
    -0.11
     thereby
    -0.11
     daher
    -0.10
    emit
    -0.10
    POSITIVE LOGITS
     because
    0.09
    rai
    0.08
     coz
    0.08
    because
    0.08
    apest
    0.08
     aug
    0.08
    |-
    0.07
     McCorm
    0.07
    rolling
    0.07
    cheng
    0.07
    Activations Density 0.030%

    No Known Activations