© 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. 26038
    Prev
    Next
    INDEX
    Explanations

    AND/OR conjunctions

    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
    etc
    -0.12
    wan
    -0.11
    pray
    -0.11
    ikal
    -0.11
    iage
    -0.11
    Instead
    -0.11
     Dann
    -0.11
    903
    -0.11
     Howell
    -0.11
     etc
    -0.11
    POSITIVE LOGITS
     AND
    0.37
     sowie
    0.30
     plus
    0.30
     ainsi
    0.28
    AND
    0.27
     PLUS
    0.26
    åıĬ
    0.23
     oraz
    0.21
     samt
    0.18
     OR
    0.18
    Activations Density 1.878%

    No Known Activations