© 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. 25813
    Prev
    Next
    INDEX
    Explanations

    sentence endings

    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
     met
    -0.10
     uns
    -0.08
    andr
    -0.08
    FAST
    -0.08
    uma
    -0.08
    quit
    -0.08
    Mahon
    -0.08
    imore
    -0.08
     ETA
    -0.08
     bypass
    -0.08
    POSITIVE LOGITS
     Guill
    0.12
    bé
    0.10
     Sah
    0.10
     Destroy
    0.10
     dort
    0.09
     Retry
    0.09
     visita
    0.09
     stab
    0.09
     Aad
    0.09
    oup
    0.09
    Activations Density 0.303%

    No Known Activations