© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 6237
    Prev
    Next
    INDEX
    Explanations

    should, have, has, come, got

    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
     certainly
    -0.16
     surely
    -0.12
     definitely
    -0.11
     Slater
    -0.11
     immediately
    -0.11
     Certainly
    -0.11
    enan
    -0.11
     Kap
    -0.10
     mildly
    -0.10
     Rav
    -0.10
    POSITIVE LOGITS
     estate
    0.11
    ,re
    0.10
     McCoy
    0.09
    YY
    0.09
    ignment
    0.09
    -life
    0.08
    ardo
    0.08
     guts
    0.08
     messed
    0.08
     Floors
    0.08
    Activations Density 0.159%

    No Known Activations