© 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. 88715
    Prev
    Next
    INDEX
    Explanations

    Microsoft, Apple, Google executive news

    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
     niche
    -0.10
     targ
    -0.09
     proport
    -0.09
    affiliate
    -0.09
     Commonwealth
    -0.09
     Xt
    -0.08
    æ¥
    -0.08
     national
    -0.08
    Sharper
    -0.08
     sufferers
    -0.08
    POSITIVE LOGITS
     Alphabet
    0.16
     Cupertino
    0.15
     Jobs
    0.13
     philanth
    0.13
     hardware
    0.13
     billions
    0.13
     secretive
    0.13
     Siri
    0.12
     Apple
    0.12
     internally
    0.12
    Activations Density 1.200%

    No Known Activations