© 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. 50498
    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
     Firstly
    -0.08
    atr
    -0.08
     irr
    -0.08
    atron
    -0.07
     hel
    -0.07
    roupon
    -0.07
    ubre
    -0.07
     aston
    -0.07
    hel
    -0.07
     Recreation
    -0.07
    POSITIVE LOGITS
     truly
    0.17
     Truly
    0.16
     life
    0.16
     love
    0.13
     Life
    0.13
    otta
    0.13
     cent
    0.12
     such
    0.12
     progress
    0.12
     Such
    0.12
    Activations Density 0.046%

    No Known Activations