© 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. 114412
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by sentence start

    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
     goodwill
    -0.12
    Then
    -0.12
     Kem
    -0.12
     Then
    -0.12
    idel
    -0.12
    vice
    -0.12
     THEN
    -0.11
     consequently
    -0.11
     Fine
    -0.11
    /on
    -0.11
    POSITIVE LOGITS
     especially
    0.13
     Especially
    0.11
    especially
    0.10
     obviously
    0.10
     everything
    0.09
     Firstly
    0.09
     firstly
    0.09
     oft
    0.09
     theres
    0.09
     Everything
    0.08
    Activations Density 0.175%

    No Known Activations