© 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. 88580
    Prev
    Next
    INDEX
    Explanations

    just, is, well, the

    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
    kee
    -0.10
    /Peak
    -0.10
    /Dk
    -0.09
    icks
    -0.09
     Desert
    -0.09
     Wax
    -0.09
    ARGV
    -0.09
     Lawson
    -0.08
     Monkey
    -0.08
    ych
    -0.08
    POSITIVE LOGITS
    âĢ¦
    0.24
     exactly
    0.22
     indeed
    0.22
    ...
    0.21
    âĢ¦the
    0.19
    âĢ¦.
    0.18
     âĢ¦
    0.18
     Indeed
    0.17
    âĢ¦..
    0.17
     just
    0.17
    Activations Density 0.372%

    No Known Activations