© 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. 5388
    Prev
    Next
    INDEX
    Explanations

    including and plus

    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
     ÑĩÑĤо
    -0.10
    pls
    -0.09
     ogl
    -0.09
    ovich
    -0.09
     ص
    -0.09
    ouri
    -0.09
     Nev
    -0.08
     коÑĤоÑĢÑĭй
    -0.08
     belum
    -0.08
    uru
    -0.08
    POSITIVE LOGITS
     along
    0.43
    along
    0.39
     Along
    0.33
    Along
    0.32
     ainsi
    0.29
     alongside
    0.29
    åıĬ
    0.26
     sowie
    0.24
     plus
    0.21
     Dit
    0.21
    Activations Density 0.655%

    No Known Activations