© 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. 117021
    Prev
    Next
    INDEX
    Explanations

    stand out, stand behind, stand ready

    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
    ATS
    -0.10
    links
    -0.09
     trade
    -0.09
    abbo
    -0.08
     Lid
    -0.08
     lid
    -0.08
    Hit
    -0.08
    ergency
    -0.08
    lid
    -0.08
    fty
    -0.08
    POSITIVE LOGITS
     testament
    0.13
     firm
    0.13
     taller
    0.11
     tall
    0.11
    /site
    0.11
    -alone
    0.11
     Equal
    0.11
     testimony
    0.11
     Tall
    0.11
     equal
    0.11
    Activations Density 0.040%

    No Known Activations