© 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. 113332
    Prev
    Next
    INDEX
    Explanations

    then, punctuation followed by pronouns

    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
    ester
    -0.10
     however
    -0.10
     HOWEVER
    -0.09
    crc
    -0.09
    rin
    -0.09
    iser
    -0.09
    ala
    -0.09
     MAS
    -0.09
    oger
    -0.09
    .mas
    -0.09
    POSITIVE LOGITS
    ï¼ĮåĪĻ
    0.15
     surely
    0.14
    then
    0.13
     then
    0.13
     firstly
    0.13
    åĪĻ
    0.12
     unavoid
    0.12
     Surely
    0.12
     ÑĤо
    0.12
    	then
    0.12
    Activations Density 0.277%

    No Known Activations