© 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. 112670
    Prev
    Next
    INDEX
    Explanations

    because

    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
    335
    -0.09
    ven
    -0.08
    ume
    -0.08
     Pou
    -0.07
    uth
    -0.07
    DP
    -0.07
    irk
    -0.07
     quietly
    -0.07
     conj
    -0.07
    405
    -0.07
    POSITIVE LOGITS
     because
    0.30
    because
    0.29
     Because
    0.25
    Because
    0.25
     porque
    0.23
    åĽł
    0.22
     parce
    0.21
     omdat
    0.18
    ecause
    0.17
     åĽ
    0.16
    Activations Density 0.816%

    No Known Activations