© 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. 14572
    Prev
    Next
    INDEX
    Explanations

    then, followed by verbs or punctuation

    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
     then
    -0.22
    then
    -0.21
    	then
    -0.18
    _then
    -0.17
    Then
    -0.16
     Then
    -0.16
     THEN
    -0.15
    åĪĻ
    -0.15
     ÑĤо
    -0.14
    THEN
    -0.14
    POSITIVE LOGITS
    umber
    0.17
    ew
    0.13
    abouts
    0.13
    ìĦľ
    0.13
    -current
    0.13
    etwork
    0.12
    ext
    0.12
    -President
    0.12
    moz
    0.12
    ews
    0.11
    Activations Density 0.110%

    No Known Activations