© 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. 116565
    Prev
    Next
    INDEX
    Explanations

    start by saying

    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
     incapac
    -0.11
     dil
    -0.11
     wink
    -0.10
    still
    -0.09
     Dil
    -0.09
    next
    -0.09
     next
    -0.09
     seiz
    -0.09
     Garc
    -0.09
     diluted
    -0.08
    POSITIVE LOGITS
     upfront
    0.22
     firstly
    0.21
     first
    0.21
     Firstly
    0.20
     disclaimer
    0.20
    åħĪ
    0.18
     outset
    0.18
     preamble
    0.18
    é¦ĸ
    0.18
     Disclaimer
    0.17
    Activations Density 0.216%

    No Known Activations